US20130332441A1 - Systems and Methods for Identifying Terms Relevant to Web Pages Using Social Network Messages - Google Patents

Systems and Methods for Identifying Terms Relevant to Web Pages Using Social Network Messages Download PDF

Info

Publication number
US20130332441A1
US20130332441A1 US13/968,103 US201313968103A US2013332441A1 US 20130332441 A1 US20130332441 A1 US 20130332441A1 US 201313968103 A US201313968103 A US 201313968103A US 2013332441 A1 US2013332441 A1 US 2013332441A1
Authority
US
United States
Prior art keywords
terms
web page
list
relevant
web
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US13/968,103
Inventor
Daniel Benyamin
Aaron Chu
Michael Aaron Hall
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CitizenNet Inc
Original Assignee
CitizenNet Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to US28594409P priority Critical
Priority to US12/966,921 priority patent/US8554854B2/en
Application filed by CitizenNet Inc filed Critical CitizenNet Inc
Priority to US13/968,103 priority patent/US20130332441A1/en
Publication of US20130332441A1 publication Critical patent/US20130332441A1/en
Assigned to CITIZENNET INC. reassignment CITIZENNET INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: HALL, MICHAEL, BENYAMIN, DANIEL, CHU, AARON
Abandoned legal-status Critical Current

Links

Images

Classifications

    • G06F17/30864
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/951Indexing; Web crawling techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06QDATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/10Office automation, e.g. computer aided management of electronic mail or groupware; Time management, e.g. calendars, reminders, meetings or time accounting
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L51/00Arrangements for user-to-user messaging in packet-switching networks, e.g. e-mail or instant messages
    • H04L51/32Messaging within social networks

Abstract

Systems and methods for retrieving social network messages and/or web pages in response to search queries are described. One embodiment of the invention includes generating a word list from at least a portion of the content of the web page using a web and message server system, generating an initial list of relevant terms based upon the word list using the web and message server system, identifying additional relevant terms using messages posted to at least one social network based upon the initial list of relevant terms, and creating an updated list of relevant terms by using the web and server system to combine terms in the initial list of relevant terms with the additional relevant terms identified using messages posted to at least one social network.

Description

    RELATED APPLICATIONS
  • This application is a continuation of U.S. patent application Ser. No. 12/966,921, filed Dec. 13, 2010. U.S. patent application Ser. No. 12/966,921 claims priority to U.S. Provisional Patent Application No. 61/285,944, filed Dec. 11, 2009. The disclosure of U.S. patent application Ser. No. 12/966,921 and U.S. Provisional Patent Application No. 61/285,944 are hereby incorporated by reference in their entirety.
  • BACKGROUND
  • The invention generally relates to messaging in social networks, and more particularly relates to matching messages to web pages.
  • Due to the tremendous amount of information available on the Internet, finding the most appropriate information or content that a searcher is looking for can be quite difficult. Likewise, locating and/or associating or linking messages from a social network with relevant content, e.g., web pages, can prove even more difficult given the inherent limited nature of the messages in both content and actual characters in the messages.
  • SUMMARY OF THE INVENTION
  • Systems and methods for retrieving social network messages and/or web pages in response to search queries in accordance with embodiments of the invention are described. One embodiment of the invention includes generating a word list from at least a portion of the content of the web page using a web and message server system, generating an initial list of relevant terms based upon the word list using the web and message server system, identifying additional relevant terms using messages posted to at least one social network based upon the initial list of relevant terms, and creating an updated list of relevant terms by using the web and server system to combine terms in the initial list of relevant terms with the additional relevant terms identified using messages posted to at least one social network.
  • In a further embodiment of the invention generating a word list from at least a portion of the content of the web page using a web and message server system includes extracting desired content from the web page, and generating a list of words utilized in the extracted web page content.
  • In another embodiment of the invention the desired content extracted from the web page includes content from the group made up of the title, URL, links, and body of the web page.
  • In a still further embodiment of the invention, extracting desired content from the web page includes performing document object model analysis on the web page.
  • In still another embodiment of the invention, generating a list of words utilized in the extracted web page content includes generating a list of words that appear in the extracted web page content, filtering the list of words to eliminate words identified in a predetermined list of stop words, and filtering the list of words to remove case and tense variants of words.
  • In a yet further embodiment of the invention, generating an initial list of relevant terms based upon the word list using the web and message server system includes generating combinations of words that appear as neighboring words in the extracted web page content, and combining the word combinations with the list of individual words to generate the initial list of relevant terms.
  • In yet another embodiment of the invention, each of the generated combinations is limited to a predetermined number of words.
  • A further embodiment of the invention again also includes scoring each term in the initial list of terms with respect to at least the extracted content from the web page.
  • In another embodiment of the invention again, scoring each of the terms with respect to at least the extracted content from the web page includes scoring each term based upon at least one characteristic including a characteristic from the group made up of the number of occurrences of the term in the extracted web page content, the number of occurrences of the term in the original web page, the uniqueness of the term, the position of the term on the web page, and combinations thereof.
  • In a further additional embodiment, uniqueness of a term is determined based upon the message rate of the term within at least one message stream.
  • In another additional embodiment, the uniqueness of a term increases below a predetermined threshold, and the uniqueness of a term decreases above the predetermined threshold.
  • In a still yet further embodiment, identifying additional relevant terms using messages posted to at least one social network based upon the initial list of relevant terms includes determining the uniqueness of all combinations of a predetermined selection of the highest scoring terms from the initial list of relevant terms, and selecting combinations of the terms based upon the uniqueness of the combination.
  • In still yet another embodiment, uniqueness of a combination of terms is determined based upon the message rate of the combination of terms within at least one message stream.
  • In a still further embodiment again, the uniqueness of the combination of terms increases below a predetermined threshold, and the uniqueness of the combination of terms decreases above the predetermined threshold.
  • In still another embodiment again, the predetermined selection of the highest scoring terms from the initial list of relevant terms is a predetermined number of the terms from the initial list with the highest scores.
  • In a still further additional embodiment, the predetermined selection of the highest scoring terms from the initial list of relevant terms includes all terms from the initial list with scores exceeding a predetermined threshold.
  • In still another additional embodiment, creating an updated list of relevant terms by using the web and server system to combine terms in the initial list of relevant terms with the additional relevant terms identified using messages posted to at least one social network scoring each combination of terms with respect to at least the extracted content from the web page, and adding the combinations of terms to the initial list of terms.
  • A yet further embodiment again also includes sorting the combinations of terms and the terms in the initial list of terms based upon score, and selecting an updated list based upon a predetermined selection of the highest scoring terms from the sorted list.
  • In yet another embodiment again, scoring each combination of terms with respect to at least the extracted content from the web page includes scoring each combination of terms based upon at least one characteristic including a characteristic from the group made up of the number of occurrences of the term in the extracted web page content, the number of occurrences of the term in the original web page, the uniqueness of the term, the position of the term on the web page, and combinations thereof.
  • In a yet further additional embodiment, identifying additional relevant terms using messages posted to at least one social network based upon the initial list of relevant terms includes retrieving messages by querying at least one social network using terms from the initial list of terms, and generating an additional list of relevant terms based upon the retrieved messages.
  • In yet another additional embodiment, generating an additional list of relevant terms based upon the retrieved messages includes generating a list of words that appear in the retrieved messages, filtering the list of words to eliminate words identified in a predetermined list of stop words, filtering the list of words to remove case and tense variants of words, generating combinations of words that appear as neighboring words in the retrieved messages, and combining the word combinations with the filtered list of individual words to generate the additional list of relevant terms.
  • In another further embodiment, creating an updated list of relevant terms by using the web and server system to combine terms in the initial list of relevant terms with the additional relevant terms identified using messages posted to at least one social network includes scoring the terms in the additional list of relevant terms based upon messages retrieved from a social network, and adding the scored terms to the initial list of relevant terms.
  • In still another further embodiment, retrieving messages by querying at least one social network using terms from the initial list of terms further includes determining the topic of the web page, and scoring the terms in the additional list of relevant terms using a set of messages having relevancy to the topic of the webpage.
  • In yet another further embodiment, scoring the terms in the additional list of relevant terms using messages having relevancy to the topic of the webpage includes scoring each term in the additional list of relevant terms based upon at least one characteristic including a characteristic from the group made up of the number of occurrences of the term in the set of messages having relevancy to the topic of the web page, the uniqueness of the term, the position of the term in each message, and combinations thereof.
  • In another further embodiment again, adding the scored terms to the initial list of relevant terms further includes adding a predetermined selection of the highest scoring terms from the additional list of relevant terms.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1 is a block diagram illustrating a web page and messaging search and retrieval system in accordance with an embodiment of the invention.
  • FIG. 2 is a flowchart illustrating a web page and messaging search and retrieval process in accordance with an embodiment of the invention.
  • FIG. 3 is a graphical representation of a score versus message rate in accordance with an embodiment of the invention.
  • FIG. 4 is a flowchart illustrating a process for filtering messages based upon topic relevancy in accordance with an embodiment of the invention.
  • DESCRIPTION
  • Turning now to the drawings, systems and methods for retrieving social network messages and/or web pages in response to search queries in accordance with embodiments of the invention are illustrated. In several embodiments, search results are improved by matching social network messages to web pages in order to obtain additional information concerning the relevancy of search terms to specific web pages. Social network messages are typically short messages that can incorporate unique terminology adapted to the constraints of the messaging medium. In several embodiments, an initial list of relevant terms is generated based upon a specific web page. The initial list of relevant terms is then used to generate an expanded list of relevant terms based upon terms used in social network messages using techniques including but not limited to static phrase expansion and/or dynamic phrase expansion.
  • The term static phrase expansion can be used to refer to processes for assigning relevancy scores to phrases constructed using keywords extracted from a web page by analyzing the message rates of messages in a social network that contain the constructed phrases. The message rates provide information concerning the relevancy and uniqueness of the constructed phrase. The message rates can be used to sort or rank the constructed phrases and optionally the bottom or low/lowest scored phrases can be removed or ignored. In addition, phrases that appear with a frequency above a predetermined rate can also be ignored on the basis that the terms are common and not indicative of relevance with the web page.
  • The term dynamic phrase expansion can be used to refer to processes for generating an expanded list of relevant search terms by querying one or more social networks using an initial list of search terms, and identifying additional relevant terms used in the social network messages returned by the social network. It should be appreciated that the terms obtained by dynamically analyzing messages retrieved from the one or more social networks will likely include different or “new” terms (i.e. terms not found/used in the web page) since social network message limits are typically finite, often summarize thoughts and/or reflect a deliberate or thoughtful choice of words.
  • In many embodiments, the information parsed from each web page can include but is not limited the title, universal resource locator (URL), description tag, keywords tag, and/or main body of the page. Keywords are extracted from the parsed information. In several embodiments, the keywords are extracted using keyword extraction techniques based on term frequency. Although any of a variety of keyword extraction techniques can be utilized in accordance with embodiments of the invention. Scores are assigned to and used to rank the extracted keywords by looking for the existence of the particular keyword in the title, URL, links, and body of the page. In several embodiments, the initial list of relevant terms is not limited to keywords, and includes phrases. The initial list of relevant terms or a portion of the initial list can then be used as a search criteria in a social network, and messages can be gathered that match the search criteria and used to perform static and/or dynamic phrase expansion to create an expanded list of relevant search terms. The expanded list of relevant search terms can then be used in the retrieval of web pages and/or social network messages in response to search queries. The generation of lists of terms relevant to specific web pages, expanding the lists of relevant terms based upon social network messages using processes including but not limited to static phrase expansion and/or dynamic phrase expansion, and the retrieval of web pages and/or social network messages in response to search queries using expanded lists of relevant search terms are discussed further below.
  • System Architecture
  • In FIG. 1, a web page and message search and retrieval system is shown. The system includes a web and message server 3 that is coupled with a web page and message database 5 and is in network communication with a plurality of messaging and web services and information sources 7. The web and message server and the web and message database can collectively be considered a web and message server system. In many embodiments, a web and message server system can include more than one server and more than one database. In addition, the web and message server system can include additional servers performing functions including but not limited to serving web pages enabling users to interact with the web and message server system via web based user interfaces. Web and message servers and web and message databases in accordance with embodiments of the invention are discussed further below.
  • In the illustrated embodiment, the web and message server receives web pages from remote servers and generates a record for each received web page in the web and message database. In several embodiments, at least a portion of the received web page is associated with the page's record within the web and message database. The web and message server extracts a list of terms from at least a portion of the web page and the list of terms is associated with the page's record. In many embodiments, each term is scored based upon its relevancy to the web page and the scores are also associated with the keywords in the page's record.
  • In many embodiments, the web and message server is also configured to receive user generated messages from a plurality of messaging services and information sources including but not limited to the Facebook service provided by Facebook, Inc., the Twitter service provided by Twitter, Inc., and/or the Linked In service provided by LinkedIn, Inc. In many embodiments, the received messages are also stored and/or associated with records in the web and message database. In a number of embodiments, keywords are selected from the received messages and utilized in the identification of additional terms relevant to web pages for which records exist in the database.
  • As noted above, the web and message server 3 can also receives search queries from user devices 8 either indirectly via, for example, messaging services or web servers 7 or directly, for example, through a user interface in communication with the web and message server. Examples of user devices include but are not limited to personal computers, mobile phones, and other types of web connected consumer electronics devices such as tablets, cable boxes, DVD players, and televisions. For each received search query, the web and message server identifies records within the message and web database that are relevant to the search query. The identified records can relate to social network messages and/or web pages and information from the identified records can be retrieved from the database 5 by the server 3 and transmitted back to a designated recipient, e.g., the sender of the search query. In many embodiments, the information can include but is not limited to relevant social network messages and/or URLs of relevant web pages. In several embodiments, information extracted from the web page indicated by the URL is also provided in conjunction with each URL to assist a user in evaluating the web page or message that is actually of most interest to them. Processes for identifying search terms relevant to web pages and or social network messages and for retrieving web pages and/or social network messages in response to a search query in accordance with various embodiments of the invention are discussed further below.
  • Identifying Relevant Search Terms
  • Referring now to FIG. 2, a process for identifying search terms relevant to a web page in accordance with an embodiment of the invention is shown. When identifying relevant search terms, a given candidate web page is identified and retrieved (41). In many embodiments, undesired content from the web page is then removed or otherwise ignored. The undesired content can include but is not limited to navigational content, advertisements, interactive material, and other content that is not particularly relevant to the intent of the page when viewed by a user. In many embodiments, the title, URL, links, and body of the web page are desired content that is extracted from the web page for use. One technique for performing such a removal is document object model (DOM) analysis. Although other techniques suitable for removal of information can be utilized in accordance with the requirements of a specific application.
  • From the reduced web page or the extracted content from the web page, a list of words from the page is created (42). In generating the word list, “stop” words (e.g., common words in a language, such as prepositions) are removed and in one embodiment all case and tense variants of a word are also removed. For example “skateboard” “skateboarding” “skateboarder” all become three cases of one word, “skateboard”. From the word list, words are combined or stringed together to build phrases (43). In several embodiments, phrases are built using words from the word list by grouping all combinations of up to a particular number, “N”, of neighboring words into a phrase.
  • The generated phrases are then applied to the reduced web page and/or in many embodiments the original web page resulting in a score for each of the phrases (44). In several embodiments, each of the phrases are scored based upon the number of occurrences in the document, uniqueness, the position on the page, if the terms exist in links or the page's title or URL, and other identified criteria. The phrases or the words in each of the phrases are then ranked utilizing the scores for each of the phrases in which the word appears (45). Term uniqueness is described in greater detail below. Once an initial list of terms has been generated, the initial list of terms can be expanded by utilizing the initial list to identify additional relevant terms in social network messages and/or one or message streams. Various techniques for expanding an initial list of relevant terms including static phrase expansion, and dynamic phrase expansion in accordance with embodiments of the invention are discussed below.
  • Static Phrase Expansion
  • In several embodiments, additional or new phrases are generated using static phrase expansion, dynamic phrase expansion or a combination thereof (46). Static phrase expansion is done by calculating the uniqueness of all combinations of the top scoring N phrases, and removing combinations that score above a specified uniqueness threshold. For example, in one embodiment, a uniqueness score that is too high means that the combination would produce too few messages, if any. For example, if the top two terms from the previous described ranking are “skateboard” and “safety”, a new term “skateboard safety” is generated and calculated for uniqueness. Estimation of term uniqueness is described in greater detail below. A score is then generated for these expanded phrases or phrases with the new expanded terms. In many embodiments, the new phrases are then applied to the reduced web page and/or in several embodiments the original web page resulting in a score for each of the phrases. In a number of embodiments, each of the phrases are scored based upon the number of occurrences in the document, uniqueness, the position on the page, if the terms exist in links or the page's title or URL, and other identified criteria. In several embodiments, by utilizing the original phrase scores and the uniqueness of the expanded phrase, the scores for the expanded phrases are generated. The entire list of phrases is sorted by their score and only a specific number of phrases are kept, e.g., the top M phrases. Where appropriate, case or tense variants are removed, and additional new phrases are supplied that include these tense or case variants.
  • Dynamic Phrase Expansion
  • In several embodiments, in order to also provide content that may be “hot” or especially relevant at a specific moment, dynamic phrase expansion can be conducted. In many embodiments, the N highest scoring terms for a web page can be used as search queries in a social network and the search results analyzed to generate a list of new terms using techniques similar to those outlined above with respect to the construction of an initial list of relevant terms from a web page. In a number of embodiments, the new terms are then scored using a set of messages including but not limited to a stream of messages, and/or a predetermined set of messages satisfying specific criteria. Examples of appropriate criteria include but are not limited to messages sent during a set period of time, or messages having a particular topic relevancy. In several embodiments, each of the terms are scored based upon the number of occurrences in the message, uniqueness, the position in the message, if the terms exist in links or other associated content, and/or in accordance with other criteria appropriate to a specific application. These new phrases may optionally be added to the list of relevant terms for the document, or concatenated with the original set of relevant terms. In several embodiments, only terms exceeding a predetermined threshold score and/or a predetermined number of the highest scoring terms are added to the initial list of relevant terms.
  • In one embodiment, a search for the top M scoring phrases is conducted via candidate social networks. This search results in some number of social messages that contain the search phrases. Although the messages may contain the candidate phrase, they may not be appropriate for the given web page. For example, a phrase that is semantically ambiguous may provide messages not appropriate for the page. Or the message may be simply “off-topic”, where the message may contain the desired phrase but little other information relevant to the page. To remove these messages, the topic of the given web page can be determined, and the topic used to filter messages that are not related to this topic. Techniques for determining the topic of a web page and the topic relevancy of a message are discussed further below.
  • Additional constraints can also be applied to the message results when attempting to identify additional terms relevant to a specific web page. For example, additional criteria could be applied to remove or retain messages matching the criteria, e.g., messages that link to multimedia content, or messages from a certain user.
  • Determined Phrases
  • Referring back to FIG. 2, once relevant terms, whether phrases or keywords, are determined for a given web page or pages, the phrases or keywords are associated with the web page or pages (47). In one embodiment, the phrases and/or keywords are stored as metadata with the web page, the portions extracted from the web page and/or are associated with the web page's URL. The terms can then be used to assist in the identification of web pages relevant to a specific search query. In many embodiments, the scored terms are the sole basis for the determination of relevancy. In other embodiments, the scored terms can be utilized in conjunction with other characteristics of the web page to score the relevance of the web page to a specific search query.
  • Estimation of Term Uniqueness
  • As noted above, term uniqueness can be a factor utilized in scoring the relevancy of terms to a particular piece of content such as a web page, content extracted from a web page, or a message on a social network. A message stream is a time ordered set of messages in which the messages are short and/or limited to a specific number of words or characters, e.g., 140 characters. In one embodiment, given a search term, the average number of messages containing the search term (keyword) during a fixed period of time is found. The average number of messages versus the fixed time period is the message rate. The lower the message rate the more unique the search term. Utilizing a message rate, unique search terms can be determined for a given category or topic specifically pertaining to the given category or topic. In several embodiments, the optimal number of messages for a fixed period of time can be determined to further refine or enhance the search results. For example, zero search results would indicate that the phrase may not really exist, and too high a search frequency would indicate that the phrase is too common.
  • A score can be determined via a function similar to the function depicted in the chart shown in FIG. 3. According to this function, a zero message rate would receive a zero score, and high messages would also receive a low score. However, very low message rates would also receive a poor score. Although a specific function is illustrated in FIG. 3, any of a variety of functions appropriate to specific applications can be utilized in accordance with embodiments of the invention including functions in which uniqueness score increases with message score up to a threshold message rate, and uniqueness score decreases with message score above the threshold message rate.
  • Web Page Topic Mapping
  • When using social network messages to identify terms relevant to a web page, the ability to determine the topic of a web page can be useful in identifying a set of social network messages relevant to the topic of the web page. In several embodiments, the topic of a web page can be determined by comparing the web page being analyzed to a listing of web pages broken down by topic or categories. These categories form a multi-level hierarchy, or tree structure. For example, a first-level category may be “Sports”. Within this category, there may be additional categories “Basketball”, “Baseball”, and “Football”. Within “Basketball”, there may be the categories “College” and “Professional”. Thus, “Sports->Basketball->College” is a three level deep category. These listing may also include web page titles, descriptions or excerpts, and the category they belong to. Since there may be thousands of nested categories, it may be useful to coalesce these categories into a simplified tree that is only N levels in depth. For example, if a tree with a maximum depth of two levels is desired, then all pages about the topic “Basketball” would be in “Sports->Basketball”, regardless if they are from the “College” or “Professional” categories.
  • In several embodiments, the comparison between the web page being analyzed and the web page topics can be performed by calculating the TF-IDF (term frequency-inverse document frequency) values for every term in at least a portion of the every web page in each N level deep category. An inverted index of all these terms can also be generated that maps a term to a topic (an N level deep category) for fast retrieval of the information. The topic relevancy of the web page can then be performed by comparing the cosine similarity of all the text in the candidate web page with every indexed topic. The indexed topic that provides the highest cosine similarity score can be chosen as the topic of the candidate web page. Although a process for determining website topic relevancy using TF-IDF calculations and cosine similarity comparisons is disclosed above, any of a variety of processes for determining web page relevancy appropriate to a specific application can be utilized in accordance with embodiments of the invention.
  • Topic Relevance of Social Network Messages
  • Once the topic of the web page has been determined, the topic can be used to identify social network messages that are relevant to the same or an equivalent topic. In a number of embodiments, the relevance of a social network message to a specific topic can be scored by comparing keywords in the message against a list of keywords relevant to the specific topic. A process for generating lists of keywords relevant to specific topics and scoring the relevancy of individual messages to a specific topic are discussed further below.
  • Categories and Keywords
  • Categories of interest or topics can be generated by identifying a specific subject, such as a person, place or an object. In many embodiments, categories are refined based on usage performance. In particular, categories focused on things perform well with narrower descriptions having better performance. For example, a category such as “sports” would not perform as well as “basketball”, which would not perform as well as “UCLA basketball”. These fine grained categories however can come at the cost of increased processing time and storage. In several embodiments, each category is unique having no overlap with other categories.
  • For each category generated, one or more keywords are identified and associated with each category. The keywords associated with each category come from messages in the desired medium (e.g., messaging service). As such, in one embodiment, within each category, there is a specific table with one or more specific keywords for each medium. Each medium can have different message formats and/or terminology used. For example, text messages from a mobile phone can and will often look quite different from messages posted to Facebook. Thus, keywords from other sources in one embodiment are only used as a search query/filter with respect to the desired message format. In this way the keyword tables would account for slang terms and other such differentiators specific to the medium. One or more of the following processes can be used to identify the keywords that are associated with a specific category. Although specific examples are provided below, any of a variety of techniques can be utilized to build lists of keywords relevant to specific topics as appropriate to specific applications.
  • Unambiguous Training
  • For a given category, e.g., musical artists, there can be ambiguous and unambiguous terminology. For example, an artist name can be ambiguous (“the Beatles”) or unambiguous (“Paul McCartney”). Utilizing unambiguous terminology, every keyword used in a message containing “Paul McCartney” would be stored, and the usage frequencies of the keywords would be used as a measure of how related to the musical artist category a given query would be.
  • User Tagging
  • A message database in one embodiment would allow for manual tagging of information. These tags are created by users as a means to self-classify messages. One example is preceding a tag name with a unique character, e.g., a “#” character. For example, if a message contains “#oscars”, then presumably the message is about the Academy Award Ceremony, commonly referred to as “the Oscars”. As such, keywords about the Oscars awards ceremony can be generated by finding every message with the “#oscars” tag, and store each of the keywords present in the located messages. The resulting table would thus include words commonly used to describe the ceremony, and thus using the table a message that did not have a “#oscars” tag could still be located.
  • Third-Party Information
  • In one embodiment, a third party database or similar resource can be used to identify keywords. For example, utilizing a resource, such as Wikipedia, as a large collection of words related to a category, a TF-IDF analysis of this resource would yield the most important keywords for a given category. Messages could be searched to locate messages that used these keywords in which each of the resulting message-based keywords are stored in the associated category's table.
  • Category and Message Scoring
  • Once lists of keywords relevant to different topics have been constructed, the relevance of a specific message to a topic can be determined using a relevance score defined by
  • score ( m , c ) = ? ? ? ( P ( ? ) ) ? indicates text missing or illegible when filed
  • where m is a given message, c is a given category, g is a keyword in the message, and P(g,c) is the normalized frequency of a message in category c containing the keyword g. The function f is a thresholding or quantization function.
  • Quantization Function f
  • Most category tables have probability distributions that follow a power-law distribution. However, the resulting tables may have a large number of small values, or conversely, a small number of large values. In such cases it may be helpful to pass this table through a quantization function. The simplest function is simply a threshold, by which any keywords that do not pass the threshold have frequencies set to 0. More complex quantizers are used to simplify the table, boost certain values, or otherwise be shaped to improve the scoring performance.
  • A final relevancy score can be defined as Wscore=score(m,cq)+wmatch., where w is a weight [0 . . . 1], score(m,cq) is the score of the message in the query's category, and match(m,q) is the percentage of keywords that match between message m and the query q. This value is used to ensure that the messages have some similarity, even if they both score high in each category.
  • Referring now to an example, if the query is “Amazon river”, then this query would rank high in a category about rivers, the Amazon jungle, or even geographical categories. This query however would score lower in categories about companies, as the term “river” would not occur very frequently in these categories. Similarly, the message “Hiked to the Amazon today—what a beautiful jungle this is” would also rank high in the category of geographical messages, as the keywords “hiked” and “jungle” would appear often in such categories. Finally, the message matches 50% of the terms in the query (i.e., “Amazon”), ensuring that the message has a relation to the query and not just the category as a whole.
  • Filtering Messages by Topic
  • In FIG. 4, a process for filtering messages by topic in accordance with an embodiment of the invention is illustrated. Initially, categories are determined (21). Keywords are identified and used to populate tables for each determined category (22). In one embodiment, a medium is identified and used to select tables in which to populate with the keywords identified. When queries are performed using terms relevant to a web page, the messages received in response to the search query can be scored for relevancy to the topic of the web page (23). In this way, relevancy of the messages is confirmed prior to the use of the messages for purposes including but not limited to scoring the relevancy of the query term to the web page. Although a specific process is illustrated in FIG. 4, any of a variety of processes can be utilized to identify social network messages that are relevant to the topic of a specific web page in accordance with embodiments of the invention.
  • Although the present invention has been described in certain specific aspects, many additional modifications and variations would be apparent to those skilled in the art. It is therefore to be understood that the present invention may be practiced otherwise than specifically described, including various changes in the size, shape and materials, without departing from the scope and spirit of the present invention. Thus, embodiments of the present invention should be considered in all respects as illustrative and not restrictive.

Claims (20)

What is claimed:
1. A method of identifying a list of terms relevant to a web page, comprising:
generating a word list from at least a portion of the content of the web page using a web and message server system;
generating an initial list of relevant terms based upon the word list using the web and message server system;
identifying additional relevant terms using messages posted to at least one social network based upon the initial list of relevant terms; and
creating an updated list of relevant terms by using the web and server system to combine terms in the initial list of relevant terms with the additional relevant terms identified using messages posted to at least one social network.
2. The method of claim 1, wherein generating a word list from at least a portion of the content of the web page using a web and message server system comprises:
extracting desired content from the web page; and
generating a list of words utilized in the extracted web page content.
3. The method of claim 2, wherein the desired content extracted from the web page includes content from the group consisting of the title, URL, links, and body of the web page.
4. The method of claim 2, wherein extracting desired content from the web page comprises performing document object model analysis on the web page.
5. The method of claim 2, wherein generating a list of words utilized in the extracted web page content comprises:
generating a list of words that appear in the extracted web page content;
filtering the list of words to eliminate words identified in a predetermined list of stop words; and
filtering the list of words to remove case and tense variants of words.
6. The method of claim 1, wherein generating an initial list of relevant terms based upon the word list using the web and message server system comprises:
generating combinations of words that appear as neighboring words in the extracted web page content; and
combining the word combinations with the list of individual words to generate the initial list of relevant terms.
7. The method of claim 6, wherein each of the generated combinations is limited to a predetermined number of words.
8. The method of claim 6, further comprising scoring each term in the initial list of terms with respect to at least the extracted content from the web page.
9. The method of claim 8, wherein scoring each of the terms with respect to at least the extracted content from the web page comprises:
scoring each term based upon at least one characteristic including a characteristic from the group consisting of:
the number of occurrences of the term in the extracted web page content;
the number of occurrences of the term in the original web page;
the uniqueness of the term;
the position of the term on the web page; and
combinations thereof.
10. The method of claim 9, wherein uniqueness of a term is determined based upon the message rate of the term within at least one message stream.
11. The method of claim 10, wherein:
the uniqueness of a term increases below a predetermined threshold; and
the uniqueness of a term decreases above the predetermined threshold.
12. The method of claim 1, wherein identifying additional relevant terms using messages posted to at least one social network based upon the initial list of relevant terms comprises:
determining the uniqueness of all combinations of a predetermined selection of the highest scoring terms from the initial list of relevant terms; and
selecting combinations of the terms based upon the uniqueness of the combination.
13. The method of claim 12, wherein uniqueness of a combination of terms is determined based upon the message rate of the combination of terms within at least one message stream.
14. The method of claim 13, wherein:
the uniqueness of the combination of terms increases below a predetermined threshold; and
the uniqueness of the combination of terms decreases above the predetermined threshold.
15. The method of claim 12, wherein the predetermined selection of the highest scoring terms from the initial list of relevant terms is a predetermined number of the terms from the initial list with the highest scores.
16. The method of claim 12, wherein the predetermined selection of the highest scoring terms from the initial list of relevant terms includes all terms from the initial list with scores exceeding a predetermined threshold.
17. The method of claim 12, wherein creating an updated list of relevant terms by using the web and server system to combine terms in the initial list of relevant terms with the additional relevant terms identified using messages posted to at least one social network comprises:
scoring each combination of terms with respect to at least the extracted content from the web page; and
adding the combinations of terms to the initial list of terms.
18. The method of claim 17, further comprising:
sorting the combinations of terms and the terms in the initial list of terms based upon score; and
selecting an updated list based upon a predetermined selection of the highest scoring terms from the sorted list.
19. The method of claim 17, wherein scoring each combination of terms with respect to at least the extracted content from the web page comprises:
scoring each combination of terms based upon at least one characteristic including a characteristic from the group consisting of:
the number of occurrences of the term in the extracted web page content;
the number of occurrences of the term in the original web page;
the uniqueness of the term;
the position of the term on the web page; and
combinations thereof.
20. A web and message server system, comprising:
a processor; and
a memory connected to the processor, where the memory is configured to store a web and message application;
wherein the web and message application configures the processor to:
generate a word list from at least a portion of the content of the web page;
generate an initial list of relevant terms based upon the word list;
identify additional relevant terms using messages posted to at least one social network based upon the initial list of relevant terms; and
create an updated list of relevant terms by combine terms in the initial list of relevant terms with the additional relevant terms identified based on messages posted to at least one social network.
US13/968,103 2009-12-11 2013-08-15 Systems and Methods for Identifying Terms Relevant to Web Pages Using Social Network Messages Abandoned US20130332441A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US28594409P true 2009-12-11 2009-12-11
US12/966,921 US8554854B2 (en) 2009-12-11 2010-12-13 Systems and methods for identifying terms relevant to web pages using social network messages
US13/968,103 US20130332441A1 (en) 2009-12-11 2013-08-15 Systems and Methods for Identifying Terms Relevant to Web Pages Using Social Network Messages

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US13/968,103 US20130332441A1 (en) 2009-12-11 2013-08-15 Systems and Methods for Identifying Terms Relevant to Web Pages Using Social Network Messages

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US12/966,921 Continuation US8554854B2 (en) 2009-12-11 2010-12-13 Systems and methods for identifying terms relevant to web pages using social network messages

Publications (1)

Publication Number Publication Date
US20130332441A1 true US20130332441A1 (en) 2013-12-12

Family

ID=44144108

Family Applications (2)

Application Number Title Priority Date Filing Date
US12/966,921 Active 2031-07-03 US8554854B2 (en) 2009-12-11 2010-12-13 Systems and methods for identifying terms relevant to web pages using social network messages
US13/968,103 Abandoned US20130332441A1 (en) 2009-12-11 2013-08-15 Systems and Methods for Identifying Terms Relevant to Web Pages Using Social Network Messages

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US12/966,921 Active 2031-07-03 US8554854B2 (en) 2009-12-11 2010-12-13 Systems and methods for identifying terms relevant to web pages using social network messages

Country Status (1)

Country Link
US (2) US8554854B2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130159341A1 (en) * 2010-05-27 2013-06-20 International Business Machines Corporation Metadata cache management

Families Citing this family (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090307003A1 (en) * 2008-05-16 2009-12-10 Daniel Benyamin Social advertisement network
US8549016B2 (en) * 2008-11-14 2013-10-01 Palo Alto Research Center Incorporated System and method for providing robust topic identification in social indexes
US8504550B2 (en) * 2009-05-15 2013-08-06 Citizennet Inc. Social network message categorization systems and methods
US8380697B2 (en) * 2009-10-21 2013-02-19 Citizennet Inc. Search and retrieval methods and systems of short messages utilizing messaging context and keyword frequency
US8554854B2 (en) * 2009-12-11 2013-10-08 Citizennet Inc. Systems and methods for identifying terms relevant to web pages using social network messages
WO2011123981A1 (en) * 2010-04-07 2011-10-13 Google Inc. Detection of boilerplate content
US8666979B2 (en) * 2010-04-09 2014-03-04 Palo Alto Research Center Incorporated Recommending interesting content using messages containing URLs
US8676875B1 (en) * 2010-05-19 2014-03-18 Adobe Systems Incorporated Social media measurement
US9356806B2 (en) * 2010-10-06 2016-05-31 Twitter, Inc. Prioritizing messages within a message network
US8612293B2 (en) 2010-10-19 2013-12-17 Citizennet Inc. Generation of advertising targeting information based upon affinity information obtained from an online social network
US8615434B2 (en) 2010-10-19 2013-12-24 Citizennet Inc. Systems and methods for automatically generating campaigns using advertising targeting information based upon affinity information obtained from an online social network
US20120150908A1 (en) * 2010-12-09 2012-06-14 Microsoft Corporation Microblog-based customer support
CN102651719B (en) * 2011-02-28 2016-08-31 国际商业机器公司 For the method and apparatus following the tracks of message topic in message interaction environment
US9063927B2 (en) 2011-04-06 2015-06-23 Citizennet Inc. Short message age classification
US9002892B2 (en) 2011-08-07 2015-04-07 CitizenNet, Inc. Systems and methods for trend detection using frequency analysis
KR20130049684A (en) * 2011-09-26 2013-05-14 봄 말콤 Social dialogue listening, analytics, and engagement system and method
US9276892B2 (en) * 2011-11-29 2016-03-01 Liquid Girds Social dialogue listening, analytics, and engagement system and method
US8380803B1 (en) * 2011-10-12 2013-02-19 Credibility Corp. Method and system for directly targeting and blasting messages to automatically identified entities on social media
US8949357B2 (en) * 2011-10-28 2015-02-03 Blether Labs LLC Ad hoc group chat using a social networking service
US9053497B2 (en) 2012-04-27 2015-06-09 CitizenNet, Inc. Systems and methods for targeting advertising to groups with strong ties within an online social network
US9461897B1 (en) * 2012-07-31 2016-10-04 United Services Automobile Association (Usaa) Monitoring and analysis of social network traffic
WO2014074317A1 (en) * 2012-11-08 2014-05-15 Evernote Corporation Extraction and clarification of ambiguities for addresses in documents
US9959546B2 (en) * 2013-01-23 2018-05-01 Facebook, Inc. Associating financial accounts with a social networking system user profile
US20140280178A1 (en) * 2013-03-15 2014-09-18 Citizennet Inc. Systems and Methods for Labeling Sets of Objects
GB2521637A (en) * 2013-12-24 2015-07-01 Ibm Messaging digest
CN104965826B (en) * 2014-04-18 2019-04-16 腾讯科技(深圳)有限公司 Search method and retrieval device based on browser
US9858594B2 (en) * 2014-06-30 2018-01-02 Microsoft Technology Licensing, Llc Assigning scores to electronic communications with extensions
WO2016058138A1 (en) 2014-10-15 2016-04-21 Microsoft Technology Licensing, Llc Construction of lexicon for selected context
US20160364486A1 (en) * 2015-06-11 2016-12-15 Fractal Analytics Inc. Methods and Systems for Segmenting Individuals By Interest
US20180365253A1 (en) * 2017-06-16 2018-12-20 T-Mobile Usa, Inc. Systems and Methods for Optimizing and Simulating Webpage Ranking and Traffic

Citations (48)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5649180A (en) * 1993-11-19 1997-07-15 Hitachi, Ltd. Method for generating hierarchical specification information from software
US5835087A (en) * 1994-11-29 1998-11-10 Herz; Frederick S. M. System for generation of object profiles for a system for customized electronic identification of desirable objects
US20020024532A1 (en) * 2000-08-25 2002-02-28 Wylci Fables Dynamic personalization method of creating personalized user profiles for searching a database of information
US20020194166A1 (en) * 2001-05-01 2002-12-19 Fowler Abraham Michael Mechanism to sift through search results using keywords from the results
US20030164855A1 (en) * 2002-03-01 2003-09-04 Stephen Grant Content management system
US6772150B1 (en) * 1999-12-10 2004-08-03 Amazon.Com, Inc. Search query refinement using related search phrases
US20060047701A1 (en) * 2004-08-30 2006-03-02 The Mitre Corporation Personalized broadcast news navigator
US20060190436A1 (en) * 2005-02-23 2006-08-24 Microsoft Corporation Dynamic client interaction for search
US20060248078A1 (en) * 2005-04-15 2006-11-02 William Gross Search engine with suggestion tool and method of using same
US20060253437A1 (en) * 2005-05-05 2006-11-09 Fain Daniel C System and methods for identifying the potential advertising value of terms found on web pages
US20070118508A1 (en) * 2005-11-18 2007-05-24 Flashpoint Technology, Inc. System and method for tagging images based on positional information
US20070203895A1 (en) * 2006-02-28 2007-08-30 Hossein Eslambolchi Recursive search engine using correlative words
US20080010274A1 (en) * 2006-06-21 2008-01-10 Information Extraction Systems, Inc. Semantic exploration and discovery
US20080009300A1 (en) * 2006-06-14 2008-01-10 Thanh Vuong Handheld Electronic Device and Associated Method Employing a Multiple-Axis Input Device and Arranging Words of an Existing Message Thread in Various Linguistic Categories for Selection During Text Entry
US20080189367A1 (en) * 2007-02-01 2008-08-07 Oki Electric Industry Co., Ltd. User-to-user communication method, program, and apparatus
US20080201222A1 (en) * 2007-02-16 2008-08-21 Ecairn, Inc. Blog advertising
US20080313215A1 (en) * 2007-06-13 2008-12-18 R-Web, Inc. System and method for the generation and storage of contextually anchored links and for navigation within information systems based on such links
US20090043737A1 (en) * 2007-08-09 2009-02-12 Andrew Boath Faris Systems and methods for providing a multi-function search box for creating word pages
US20090049029A1 (en) * 2005-07-27 2009-02-19 Jaekeol Choi Method and system of detecting keyword whose input number is rapidly increased in real time
US20090100042A1 (en) * 2007-10-12 2009-04-16 Lexxe Pty Ltd System and method for enhancing search relevancy using semantic keys
US20090157714A1 (en) * 2007-12-18 2009-06-18 Aaron Stanton System and method for analyzing and categorizing text
US20090164464A1 (en) * 2007-12-19 2009-06-25 Match.Com, Lp Matching Process System And Method
US20090204598A1 (en) * 2008-02-08 2009-08-13 Microsoft Corporation Ad retrieval for user search on social network sites
US20090299998A1 (en) * 2008-02-15 2009-12-03 Wordstream, Inc. Keyword discovery tools for populating a private keyword database
US20090306969A1 (en) * 2008-06-06 2009-12-10 Corneil John Goud Systems and Methods for an Automated Personalized Dictionary Generator for Portable Devices
US20090307238A1 (en) * 2008-06-05 2009-12-10 Sanguinetti Thomas V Method and system for classification of venue by analyzing data from venue website
US20100138428A1 (en) * 2007-05-08 2010-06-03 Fujitsu Limited Keyword output apparatus and method
US20100153090A1 (en) * 2008-12-09 2010-06-17 University Of Houston System Word sense disambiguation
US20100248757A1 (en) * 2009-03-31 2010-09-30 Samsung Electronics Co., Ltd. Method for creating short message and portable terminal using the same
US20100268628A1 (en) * 2009-04-15 2010-10-21 Attributor Corporation Managing controlled content on a web page having revenue-generating code
US20100293166A1 (en) * 2009-05-13 2010-11-18 Hamid Hatami-Hanza System And Method For A Unified Semantic Ranking of Compositions of Ontological Subjects And The Applications Thereof
US20100299589A1 (en) * 2009-05-19 2010-11-25 Studio Ousia Inc. Keyword display method and keyword display system
US20100332478A1 (en) * 2008-03-31 2010-12-30 Hakan Duman Electronic resource annotation
US7870135B1 (en) * 2006-06-30 2011-01-11 Amazon Technologies, Inc. System and method for providing tag feedback
US20110010357A1 (en) * 2008-06-04 2011-01-13 Soo-Hyun Kim Intellegent automatic recognition toolbar search method and system
US20110035375A1 (en) * 2009-08-06 2011-02-10 Ron Bekkerman Building user profiles for website personalization
US7890526B1 (en) * 2003-12-30 2011-02-15 Microsoft Corporation Incremental query refinement
US20110066624A1 (en) * 2006-08-01 2011-03-17 Divyank Turakhia system and method of generating related words and word concepts
US7925496B1 (en) * 2007-04-23 2011-04-12 The United States Of America As Represented By The Secretary Of The Navy Method for summarizing natural language text
US20110099186A1 (en) * 2008-05-26 2011-04-28 Kenshoo Ltd. System for finding website invitation cueing keywords and for attribute-based generation of invitation-cueing instructions
US20110125776A1 (en) * 2009-11-24 2011-05-26 International Business Machines Corporation Service Oriented Architecture Enterprise Service Bus With Advanced Virtualization
US20120221587A1 (en) * 2009-11-04 2012-08-30 Alibaba Group Holding Limited Method for Generating Search Results and System for Information Search
US20120323905A1 (en) * 2007-10-12 2012-12-20 Lexxe Pty Ltd Ranking data utilizing attributes associated with semantic sub-keys
US8375017B1 (en) * 2005-01-28 2013-02-12 Manta Media, Inc. Automated keyword analysis system and method
US8380697B2 (en) * 2009-10-21 2013-02-19 Citizennet Inc. Search and retrieval methods and systems of short messages utilizing messaging context and keyword frequency
US8504550B2 (en) * 2009-05-15 2013-08-06 Citizennet Inc. Social network message categorization systems and methods
US20130212113A1 (en) * 2006-09-22 2013-08-15 Limelight Networks, Inc. Methods and systems for generating automated tags for video files
US8554854B2 (en) * 2009-12-11 2013-10-08 Citizennet Inc. Systems and methods for identifying terms relevant to web pages using social network messages

Family Cites Families (67)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5465309A (en) * 1993-12-10 1995-11-07 International Business Machines Corporation Method of and apparatus for character recognition through related spelling heuristics
CA2211636C (en) * 1995-03-07 2002-01-22 British Telecommunications Public Limited Company Speech recognition
US6466901B1 (en) * 1998-11-30 2002-10-15 Apple Computer, Inc. Multi-language document search and retrieval system
US6515681B1 (en) * 1999-05-11 2003-02-04 Prophet Financial Systems, Inc. User interface for interacting with online message board
US6571234B1 (en) * 1999-05-11 2003-05-27 Prophet Financial Systems, Inc. System and method for managing online message board
US6766349B1 (en) * 1999-09-24 2004-07-20 Sun Microsystems, Inc. Mechanism for obtaining a thread from, and returning a thread to, a thread pool without attaching and detaching
US6571225B1 (en) * 2000-02-11 2003-05-27 International Business Machines Corporation Text categorizers based on regularizing adaptations of the problem of computing linear separators
US7421395B1 (en) * 2000-02-18 2008-09-02 Microsoft Corporation System and method for producing unique account names
JP3573688B2 (en) * 2000-06-28 2004-10-06 松下電器産業株式会社 Similar document search device and related keyword extraction device
US7047229B2 (en) * 2000-08-08 2006-05-16 America Online, Inc. Searching content on web pages
US7185065B1 (en) * 2000-10-11 2007-02-27 Buzzmetrics Ltd System and method for scoring electronic messages
US20020062368A1 (en) 2000-10-11 2002-05-23 David Holtzman System and method for establishing and evaluating cross community identities in electronic forums
US20020123928A1 (en) * 2001-01-11 2002-09-05 Eldering Charles A. Targeting ads to subscribers based on privacy-protected subscriber profiles
US7159178B2 (en) 2001-02-20 2007-01-02 Communispace Corp. System for supporting a virtual community
US7080139B1 (en) * 2001-04-24 2006-07-18 Fatbubble, Inc Method and apparatus for selectively sharing and passively tracking communication device experiences
US20040230572A1 (en) 2001-06-22 2004-11-18 Nosa Omoigui System and method for semantic knowledge retrieval, management, capture, sharing, discovery, delivery and presentation
US7089226B1 (en) 2001-06-28 2006-08-08 Microsoft Corporation System, representation, and method providing multilevel information retrieval with clarification dialog
US7734627B1 (en) * 2003-06-17 2010-06-08 Google Inc. Document similarity detection
CN1871603B (en) 2003-08-21 2010-04-28 伊迪利亚公司 System and method for processing a query
US7206814B2 (en) * 2003-10-09 2007-04-17 Propel Software Corporation Method and system for categorizing and processing e-mails
US20050204002A1 (en) 2004-02-16 2005-09-15 Friend Jeffrey E. Dynamic online email catalog and trust relationship management system and method
US7933818B1 (en) * 2004-07-13 2011-04-26 Amazon Technologies, Inc. Service for automatically detecting and responding to transition events that occur during browsing of an electronic catalog
US7603349B1 (en) 2004-07-29 2009-10-13 Yahoo! Inc. User interfaces for search systems using in-line contextual queries
WO2006039566A2 (en) 2004-09-30 2006-04-13 Intelliseek, Inc. Topical sentiments in electronically stored communications
US7953723B1 (en) * 2004-10-06 2011-05-31 Shopzilla, Inc. Federation for parallel searching
US7349896B2 (en) 2004-12-29 2008-03-25 Aol Llc Query routing
US10510043B2 (en) * 2005-06-13 2019-12-17 Skyword Inc. Computer method and apparatus for targeting advertising
US20070027751A1 (en) * 2005-07-29 2007-02-01 Chad Carson Positioning advertisements on the bases of expected revenue
US20070061195A1 (en) * 2005-09-13 2007-03-15 Yahoo! Inc. Framework for selecting and delivering advertisements over a network based on combined short-term and long-term user behavioral interests
US8903810B2 (en) * 2005-12-05 2014-12-02 Collarity, Inc. Techniques for ranking search results
US7743051B1 (en) 2006-01-23 2010-06-22 Clearwell Systems, Inc. Methods, systems, and user interface for e-mail search and retrieval
US7814112B2 (en) * 2006-06-09 2010-10-12 Ebay Inc. Determining relevancy and desirability of terms
US8301616B2 (en) * 2006-07-14 2012-10-30 Yahoo! Inc. Search equalizer
US8280921B2 (en) * 2006-07-18 2012-10-02 Chacha Search, Inc. Anonymous search system using human searchers
US7747629B2 (en) * 2006-08-23 2010-06-29 International Business Machines Corporation System and method for positional representation of content for efficient indexing, search, retrieval, and compression
US7756855B2 (en) 2006-10-11 2010-07-13 Collarity, Inc. Search phrase refinement by search term replacement
US20080140502A1 (en) * 2006-12-07 2008-06-12 Viewfour, Inc. Method and system for creating advertisements on behalf of advertisers by consumer-creators
US7958104B2 (en) * 2007-03-08 2011-06-07 O'donnell Shawn C Context based data searching
US7860928B1 (en) * 2007-03-22 2010-12-28 Google Inc. Voting in chat system without topic-specific rooms
US7617195B2 (en) * 2007-03-28 2009-11-10 Xerox Corporation Optimizing the performance of duplicate identification by content
US7657515B1 (en) * 2007-03-30 2010-02-02 Alexa Internet High efficiency document search
US7917528B1 (en) * 2007-04-02 2011-03-29 Google Inc. Contextual display of query refinements
US20080294624A1 (en) * 2007-05-25 2008-11-27 Ontogenix, Inc. Recommendation systems and methods using interest correlation
US9342551B2 (en) 2007-08-14 2016-05-17 John Nicholas and Kristin Gross Trust User based document verifier and method
US20090049127A1 (en) * 2007-08-16 2009-02-19 Yun-Fang Juan System and method for invitation targeting in a web-based social network
WO2009026395A1 (en) * 2007-08-20 2009-02-26 Facebook, Inc. Targeting advertisements in a social network
US7941437B2 (en) * 2007-08-24 2011-05-10 Symantec Corporation Bayesian surety check to reduce false positives in filtering of content in non-trained languages
US20090070346A1 (en) * 2007-09-06 2009-03-12 Antonio Savona Systems and methods for clustering information
US8442073B2 (en) * 2007-10-25 2013-05-14 Siemens Aktiengesellschaft Method and an apparatus for analyzing a communication network
US8799068B2 (en) * 2007-11-05 2014-08-05 Facebook, Inc. Social advertisements and other informational messages on a social networking website, and advertising model for same
US20090171686A1 (en) * 2008-01-02 2009-07-02 George Eberstadt Using social network information and transaction information
US9584343B2 (en) * 2008-01-03 2017-02-28 Yahoo! Inc. Presentation of organized personal and public data using communication mediums
WO2009108726A1 (en) * 2008-02-25 2009-09-03 Atigeo Llc Determining relevant information for domains of interest
US20090276285A1 (en) * 2008-05-02 2009-11-05 Yahoo! Inc. Search engine to broker advertiser with publisher
US20100049534A1 (en) * 2008-08-19 2010-02-25 Thomas Scott Whitnah Determining User Affinity Towards Applications on a Social Networking Website
US8086631B2 (en) * 2008-12-12 2011-12-27 Microsoft Corporation Search result diversification
US9521013B2 (en) * 2008-12-31 2016-12-13 Facebook, Inc. Tracking significant topics of discourse in forums
US8214357B2 (en) * 2009-02-27 2012-07-03 Research In Motion Limited System and method for linking ad tagged words
US20100306249A1 (en) 2009-05-27 2010-12-02 James Hill Social network systems and methods
US9292855B2 (en) * 2009-09-08 2016-03-22 Primal Fusion Inc. Synthesizing messaging using context provided by consumers
AU2011213606B2 (en) * 2010-02-08 2014-04-17 Facebook, Inc. Communicating information in a social network system about activities from another domain
US20120004959A1 (en) 2010-05-07 2012-01-05 CitizenNet, Inc. Systems and methods for measuring consumer affinity and predicting business outcomes using social network activity
US8612293B2 (en) 2010-10-19 2013-12-17 Citizennet Inc. Generation of advertising targeting information based upon affinity information obtained from an online social network
US8615434B2 (en) 2010-10-19 2013-12-24 Citizennet Inc. Systems and methods for automatically generating campaigns using advertising targeting information based upon affinity information obtained from an online social network
US9063927B2 (en) * 2011-04-06 2015-06-23 Citizennet Inc. Short message age classification
WO2013006440A1 (en) * 2011-07-01 2013-01-10 Dataxu, Inc. Creation and usage of synthetic user identifiers within an advertisement placement facility
US9002892B2 (en) * 2011-08-07 2015-04-07 CitizenNet, Inc. Systems and methods for trend detection using frequency analysis

Patent Citations (50)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5649180A (en) * 1993-11-19 1997-07-15 Hitachi, Ltd. Method for generating hierarchical specification information from software
US5835087A (en) * 1994-11-29 1998-11-10 Herz; Frederick S. M. System for generation of object profiles for a system for customized electronic identification of desirable objects
US6772150B1 (en) * 1999-12-10 2004-08-03 Amazon.Com, Inc. Search query refinement using related search phrases
US20020024532A1 (en) * 2000-08-25 2002-02-28 Wylci Fables Dynamic personalization method of creating personalized user profiles for searching a database of information
US20020194166A1 (en) * 2001-05-01 2002-12-19 Fowler Abraham Michael Mechanism to sift through search results using keywords from the results
US20030164855A1 (en) * 2002-03-01 2003-09-04 Stephen Grant Content management system
US7890526B1 (en) * 2003-12-30 2011-02-15 Microsoft Corporation Incremental query refinement
US20110087686A1 (en) * 2003-12-30 2011-04-14 Microsoft Corporation Incremental query refinement
US20060047701A1 (en) * 2004-08-30 2006-03-02 The Mitre Corporation Personalized broadcast news navigator
US8375017B1 (en) * 2005-01-28 2013-02-12 Manta Media, Inc. Automated keyword analysis system and method
US20060190436A1 (en) * 2005-02-23 2006-08-24 Microsoft Corporation Dynamic client interaction for search
US20060248078A1 (en) * 2005-04-15 2006-11-02 William Gross Search engine with suggestion tool and method of using same
US20060253437A1 (en) * 2005-05-05 2006-11-09 Fain Daniel C System and methods for identifying the potential advertising value of terms found on web pages
US20090049029A1 (en) * 2005-07-27 2009-02-19 Jaekeol Choi Method and system of detecting keyword whose input number is rapidly increased in real time
US20070118508A1 (en) * 2005-11-18 2007-05-24 Flashpoint Technology, Inc. System and method for tagging images based on positional information
US20070203895A1 (en) * 2006-02-28 2007-08-30 Hossein Eslambolchi Recursive search engine using correlative words
US20080009300A1 (en) * 2006-06-14 2008-01-10 Thanh Vuong Handheld Electronic Device and Associated Method Employing a Multiple-Axis Input Device and Arranging Words of an Existing Message Thread in Various Linguistic Categories for Selection During Text Entry
US20080010274A1 (en) * 2006-06-21 2008-01-10 Information Extraction Systems, Inc. Semantic exploration and discovery
US7870135B1 (en) * 2006-06-30 2011-01-11 Amazon Technologies, Inc. System and method for providing tag feedback
US20110066624A1 (en) * 2006-08-01 2011-03-17 Divyank Turakhia system and method of generating related words and word concepts
US20130212113A1 (en) * 2006-09-22 2013-08-15 Limelight Networks, Inc. Methods and systems for generating automated tags for video files
US20080189367A1 (en) * 2007-02-01 2008-08-07 Oki Electric Industry Co., Ltd. User-to-user communication method, program, and apparatus
US20080201222A1 (en) * 2007-02-16 2008-08-21 Ecairn, Inc. Blog advertising
US7925496B1 (en) * 2007-04-23 2011-04-12 The United States Of America As Represented By The Secretary Of The Navy Method for summarizing natural language text
US20100138428A1 (en) * 2007-05-08 2010-06-03 Fujitsu Limited Keyword output apparatus and method
US20080313215A1 (en) * 2007-06-13 2008-12-18 R-Web, Inc. System and method for the generation and storage of contextually anchored links and for navigation within information systems based on such links
US20090043737A1 (en) * 2007-08-09 2009-02-12 Andrew Boath Faris Systems and methods for providing a multi-function search box for creating word pages
US20090100042A1 (en) * 2007-10-12 2009-04-16 Lexxe Pty Ltd System and method for enhancing search relevancy using semantic keys
US20120323905A1 (en) * 2007-10-12 2012-12-20 Lexxe Pty Ltd Ranking data utilizing attributes associated with semantic sub-keys
US20090157714A1 (en) * 2007-12-18 2009-06-18 Aaron Stanton System and method for analyzing and categorizing text
US20090164464A1 (en) * 2007-12-19 2009-06-25 Match.Com, Lp Matching Process System And Method
US20090204598A1 (en) * 2008-02-08 2009-08-13 Microsoft Corporation Ad retrieval for user search on social network sites
US20090299998A1 (en) * 2008-02-15 2009-12-03 Wordstream, Inc. Keyword discovery tools for populating a private keyword database
US8706734B2 (en) * 2008-03-31 2014-04-22 British Telecommunications Public Limited Company Electronic resource annotation
US20100332478A1 (en) * 2008-03-31 2010-12-30 Hakan Duman Electronic resource annotation
US20110099186A1 (en) * 2008-05-26 2011-04-28 Kenshoo Ltd. System for finding website invitation cueing keywords and for attribute-based generation of invitation-cueing instructions
US20110010357A1 (en) * 2008-06-04 2011-01-13 Soo-Hyun Kim Intellegent automatic recognition toolbar search method and system
US20090307238A1 (en) * 2008-06-05 2009-12-10 Sanguinetti Thomas V Method and system for classification of venue by analyzing data from venue website
US20090306969A1 (en) * 2008-06-06 2009-12-10 Corneil John Goud Systems and Methods for an Automated Personalized Dictionary Generator for Portable Devices
US20100153090A1 (en) * 2008-12-09 2010-06-17 University Of Houston System Word sense disambiguation
US20100248757A1 (en) * 2009-03-31 2010-09-30 Samsung Electronics Co., Ltd. Method for creating short message and portable terminal using the same
US20100268628A1 (en) * 2009-04-15 2010-10-21 Attributor Corporation Managing controlled content on a web page having revenue-generating code
US20100293166A1 (en) * 2009-05-13 2010-11-18 Hamid Hatami-Hanza System And Method For A Unified Semantic Ranking of Compositions of Ontological Subjects And The Applications Thereof
US8504550B2 (en) * 2009-05-15 2013-08-06 Citizennet Inc. Social network message categorization systems and methods
US20100299589A1 (en) * 2009-05-19 2010-11-25 Studio Ousia Inc. Keyword display method and keyword display system
US20110035375A1 (en) * 2009-08-06 2011-02-10 Ron Bekkerman Building user profiles for website personalization
US8380697B2 (en) * 2009-10-21 2013-02-19 Citizennet Inc. Search and retrieval methods and systems of short messages utilizing messaging context and keyword frequency
US20120221587A1 (en) * 2009-11-04 2012-08-30 Alibaba Group Holding Limited Method for Generating Search Results and System for Information Search
US20110125776A1 (en) * 2009-11-24 2011-05-26 International Business Machines Corporation Service Oriented Architecture Enterprise Service Bus With Advanced Virtualization
US8554854B2 (en) * 2009-12-11 2013-10-08 Citizennet Inc. Systems and methods for identifying terms relevant to web pages using social network messages

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130159341A1 (en) * 2010-05-27 2013-06-20 International Business Machines Corporation Metadata cache management
US8914407B2 (en) * 2010-05-27 2014-12-16 International Business Machines Corporation Metadata cache management
US9996464B2 (en) 2010-05-27 2018-06-12 International Business Machines Corporation Metadata cache management

Also Published As

Publication number Publication date
US8554854B2 (en) 2013-10-08
US20110145348A1 (en) 2011-06-16

Similar Documents

Publication Publication Date Title
US9870423B1 (en) Associating an entity with a search query
US20170116200A1 (en) Trust propagation through both explicit and implicit social networks
US20160357860A1 (en) Natural language search results for intent queries
CN103177075B (en) The detection of Knowledge based engineering entity and disambiguation
US9846744B2 (en) Media discovery and playlist generation
Paliwal et al. Semantics-based automated service discovery
US9201880B2 (en) Processing a content item with regard to an event and a location
US9679001B2 (en) Consensus search device and method
Tsagkias et al. Linking online news and social media
US20190243838A1 (en) Tag selection and recommendation to a user of a content hosting service
Kompan et al. Content-based news recommendation
US10437892B2 (en) Efficient forward ranking in a search engine
JP2016201153A (en) Search method, search apparatus, and search engine system
AU2010208318B2 (en) Identifying query aspects
Bischoff et al. Can all tags be used for search?
US8719249B2 (en) Query classification
TWI463337B (en) Method and system for federated search implemented across multiple search engines
JP5461360B2 (en) System and method for search processing using a super unit
US8321410B1 (en) Identification of semantic units from within a search query
CN101551806B (en) Personalized website navigation method and system
JP5391633B2 (en) Term recommendation to define the ontology space
US8260664B2 (en) Semantic advertising selection from lateral concepts and topics
US7783644B1 (en) Query-independent entity importance in books
JP5572596B2 (en) Personalize the ordering of place content in search results
US8010545B2 (en) System and method for providing a topic-directed search

Legal Events

Date Code Title Description
AS Assignment

Owner name: CITIZENNET INC., CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BENYAMIN, DANIEL;CHU, AARON;HALL, MICHAEL;SIGNING DATES FROM 20101223 TO 20101228;REEL/FRAME:032234/0298

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION