CN109885656B - Microblog forwarding prediction method and device based on quantification heat degree - Google Patents
Microblog forwarding prediction method and device based on quantification heat degree Download PDFInfo
- Publication number
- CN109885656B CN109885656B CN201910119276.4A CN201910119276A CN109885656B CN 109885656 B CN109885656 B CN 109885656B CN 201910119276 A CN201910119276 A CN 201910119276A CN 109885656 B CN109885656 B CN 109885656B
- Authority
- CN
- China
- Prior art keywords
- microblog
- topic
- topics
- hot
- content
- 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.)
- Active
Links
Images
Abstract
The invention discloses a microblog forwarding prediction method and device based on quantitative popularity, wherein the method comprises the following steps: under the condition that the total daily forwarding amount of the microblog platform is not changed, determining the heat degree of each topic according to the proportion of the daily reading amount of each topic to the total daily reading amount of all topics, and sequencing microblog topics based on the heat degree of the topics to obtain a real-time microblog hot topic table; comparing the microblog content with the first N microblog topics in the microblog hot topic list, determining the hot degree of the microblog content and the microblog topics according to the correlation between the microblog content and the topic content, and accumulating the hot degree of the microblog content relative to each topic to obtain the final microblog hot degree; and predicting microblog forwarding according to the microblog popularity and the basic characteristics.
Description
Technical Field
The invention relates to the field of social network big data analysis, in particular to a microblog forwarding prediction method and device based on quantitative popularity.
Background
Compared with traditional media such as newspapers, broadcasting, televisions and the like, the microblog is mainly characterized by high message propagation speed and wide message propagation range, and hot microblogs can spread to tens of millions or even hundreds of millions of users as short as several hours from message release. The main reason why microblogs can spread messages so quickly and widely is that they are virally spread: the receiver of the message can forward the microblogs seen by the receiver of the message, the receiver of the message is changed into a publisher, numerous fans can see the microblogs forwarded by the receiver of the message, the fans can forward the microblogs again, and the microblog messages can be spread explosively in a transient mode through the virus type spreading mode. Although other propagation ways such as "@" and platform pushing also exist in the microblog, forwarding is undoubtedly the main way for promoting the microblog message to propagate in a short time and a large range. The research on the microblog forwarding behavior has important theoretical and practical significance for information dissemination, information popularization, hot event prediction, public opinion situation perception and the like.
Disclosure of Invention
The embodiment of the invention provides a microblog forwarding prediction method and device based on quantification heat degree, which are used for solving the problems in the prior art.
The embodiment of the invention provides a microblog forwarding prediction method based on quantitative popularity, which comprises the following steps:
under the condition that the total daily forwarding amount of the microblog platform is not changed, determining the heat degree of each topic according to the proportion of the daily reading amount of each topic to the total daily reading amount of all topics, and sequencing microblog topics based on the heat degree of the topics to obtain a real-time microblog hot topic table;
comparing the microblog content with the first N microblog topics in the microblog hot topic list, determining the hot degree of the microblog content and the microblog topics according to the correlation between the microblog content and the topic content, and accumulating the hot degree of the microblog content relative to each topic to obtain the final microblog hot degree;
and predicting microblog forwarding according to the microblog popularity and the basic characteristics.
Preferably, the total reading amount of all topics is the sum of the reading amounts of M topics before the microblog topic ranking in the current day.
Preferably, under the condition that the total daily forwarding amount of the microblog platform is assumed to be unchanged, determining the heat degree of each topic according to the proportion of the daily reading amount of each topic to the total daily reading amount of all topics, and sequencing microblog topics based on the heat degree of the topics to obtain a real-time microblog hot topic list specifically comprises:
continuously collecting the reading numbers of the most popular M topics every day, calculating the reading numbers increased on each topic every day, and recording as ReadTop [ i, j ], wherein the reading numbers of the topic j on the ith day are represented;
sequencing all topics according to reading amount;
calculating the total reading amount of the hottest M topics in the day according to a formula 1:
wherein Read [ i ] is the topic reading total amount of the ith day;
calculating the heat of topic j on the ith day according to formula 2:
and sequencing the topics according to the heat degree according to the calculation result of the formula 2 to obtain a real-time microblog hot topic list.
Preferably, comparing the microblog content with the first N microblog topics in the microblog trending topic table, determining the popularity of the microblog content with the microblog topic according to the correlation between the microblog content and the topic content, and accumulating the popularity of the microblog content with respect to each topic to obtain the popularity of the final microblog specifically includes:
when a microblog topic is collected, collecting Q microblogs under the microblog topic, carrying out Chinese word segmentation on the microblogs, removing stop words, calculating TF-IDF values of the rest words, taking the words with the top rank as keywords closely related to the topic, and taking the first K words as an expansion word set of the topic;
for any one microblog w, if the complete topic contained in the w is 1, determining that the similarity of the two is 1, otherwise, segmenting the w, removing stop words, constructing a word vector Vw, constructing a word vector Vh according to the topic and the expansion word set, calculating the cosine included angle of the two and taking the cosine included angle as the similarity of the w and the microblog topic h; calculating the product of the similarity and the heat of the microblog topic h, and taking the product as the heat of w relative to the topic h;
and accumulating the popularity of the microblog to the N hot topics before ranking to obtain the popularity of the final microblog.
Preferably, the basic features specifically include: user features, social features, temporal features, and content features.
The embodiment of the invention also provides a microblog forwarding prediction device based on the quantized heat degree, which comprises the following steps: a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program implementing the steps of the above method when executed by the processor.
By adopting the embodiment of the invention, the prediction effect can be effectively improved, wherein the precision is improved by 2-3%, and the recall rate is improved by 2-7%.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic diagram of a propagation process of a microblog message in an embodiment of the invention;
FIG. 2 is a schematic diagram of microblog hotness and forwarding probability in the embodiment of the invention;
FIG. 3 is a graph of a cumulative probability distribution function CDF of microblog hotness versus forwarding and ignoring in an embodiment of the invention;
fig. 4 is a processing flow chart of the microblog forwarding prediction method based on the quantized popularity in the embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
According to the embodiment of the invention, the research objects are microblog users and messages, U represents a microblog user set, W represents a microblog message set, and the microblog is supposed to be spread only through the forwarding behavior of the users. The propagation process of the microblog message is described in fig. 1: known user u0E to U, issuing a microblog W e to W, wherein the propagation path of the microblog after being forwarded for multiple times is P(u0,u1,u2…ul，um，un)，u1～umThe users that forward w on the propagation path. In FIG. 1, solid arrows indicate forwarding actions and dashed arrows indicate concerns, e.g., user umPoint unSolid arrow of (c) represents umForward ulMicroblog w, user unPoint umDotted arrow unPay attention to umThus unCan see umAnd releasing and forwarding all microblogs. From u0To umAll information such as forwarding behaviors, time, user attributes, microblog content and the like on the propagation path can be acquired through the API and the crawler. The embodiment of the invention aims to solve the problems that: when u isnSee umAnd if the microblog w is forwarded, forwarding.
Microblogs are typical social networks, the information forwarding times of the social networks conform to power rate distribution, few hot microblogs are forwarded for many times, most of the microblogs are forwarded for a few times, and users tend to forward the hot microblogs more easily. There are also two different understandings for "hot" microblogs: one is evaluated from the content perspective of the micro-blog, meaning that the content of the micro-blog is currently popular. The other is evaluated from the microblog propagation perspective, and mainly refers to which widespread microblogs are propagated. The latter can only know whether the microblog is a hot microblog or not when the microblog propagation is completed or basically completed. The former can analyze whether it is hot or not just when it is released. The hot microblog of the embodiment of the invention refers to the first definition.
The microblog popularity is the attention degree of the user to the microblog content, reflects the relation between the microblog and the current public opinion hotspot, but the popularity is a subjective feeling, and a unified and authoritative definition method is lacked. The microblog platform does not have a description about the 'hot degree' of the microblog, and through deep analysis of the hot microblog and the microblog platform, the embodiment of the invention finds two facts:
(1) most of hot microblogs are semantically related to the current hot topics;
(2) the microblog clearly marks the topics, more importantly, the microblog has real-time statistical ranking on the reading amount of each topic, and the reading amount can be easily acquired.
Based on the two phenomena, the embodiment of the invention provides an idea for objectively describing the popularity of the microblog, and the popularity of the microblog content is firstly quantified and then defined according to the similarity between the microblog and the topic.
Specifically, the invention provides a quantification method of microblog popularity to calculate the popularity value of any microblog, whether the microblog is forwarded or not is predicted based on popularity combined with other characteristics, and finally the validity of the technical scheme of the embodiment of the invention is verified on a real data set. The embodiment of the invention mainly comprises the following contents:
(1) a method for quantifying the popularity of microblog topics based on popularity competition is provided. And (3) assuming that the total forwarding amount of the microblog platform per day is unchanged, so that the heat of the topic is the proportion of the reading amount of the topic in the day to the total reading amount of all topics in the day, and providing a related calculation method.
(2) A hot degree calculation algorithm aiming at any microblog message is provided. And comparing the content of the microblog with each topic, and measuring the popularity of the microblog according to the relevance between the content of the microblog and the content of the topic and the popularity of the topic.
(3) A forwarding prediction method based on microblog popularity quantification is provided. Analysis shows that the microblog popularity is an effective characteristic for predicting microblog forwarding, and the forwarding prediction is completed by combining basic characteristics such as user characteristics, social characteristics, time characteristics, content characteristics and the like with the microblog popularity characteristics on the basis of the research of the prior people.
(4) The selection and parameter setting of the classification algorithm in the prediction method are analyzed.
The above description is only an overview of the technical solution of the present invention, and in order to more clearly understand the technical means of the present invention, the following description is taken in conjunction with the accompanying drawings, and the specific processing flow is shown in fig. 4.
Quantification method of topic popularity
A topic is identified in the micro blog with a # topic name #. The microblog topic is the subject of discussion and speaking of the user on the microblog and is abstract and summary of events concerned by the vast users. Currently, there is no definition method for the popularity of topics, but the microblog platform can sort the topics according to the reading amount by looking up the ranking lists of the topics of 1 hour and 24 hours in real time of the popular topic channels.
Therefore, hot topics and reading number of the hot topics of the microblog platform can be obtained. It should be noted that the reads collected directly through the page are the accumulated reads for the topic, not the reads while performing the prediction task. Some topics have been discussed for a long time, and although the accumulated reading number is many, the topics are not hot at present. For this situation, we only count the number of reads of the topic in the last 24 hours as the evaluation basis of the popularity. Therefore, cumulative reading of related topics needs to be collected continuously every day, so that new reading of the topics in the last 24 hours can be obtained.
Considering that the amount of information on the microblog is large and the topics are scattered, the topics and the reading number which are ranked 1000 times before are collected every day. Since the top1000 topics are dynamically changing, we also continue to collect topics that are newly entered into top1000 the next day and later. Also for topics falling out of top1000, we also collect until out of top1000 for 10 consecutive days. Through continuous collection and calculation, the hottest topic and the reading number of the hottest topic currently discussed on the microblog are obtained.
Two quantitative indicators, the ranking of topic reading and the absolute value of the reading number, are now obtained, but these two indicators cannot be used directly as indicators for evaluating the heat of a topic. This is mainly because we need to further study the relationship between topic popularity and microblog forwarding for the purpose of forwarding prediction in the present study. By continuously collecting the reading amount of the microblog hot topics every day in one week, the fact that the reading amount of the topics with the same rank in different days is large in difference is found, and if the reading amount of the second topic ranked in the first day and the second day is nearly doubled, the fact that the topic reading rank cannot be simply used for evaluating the topic popularity is shown. In addition, we found that the total reading amount on the first day and the second day is greatly different, but the forwarding numbers on the two days are not changed greatly. Although the sum of the reading numbers of the hot topics changes greatly, the total forwarding amount of the microblogs is not fluctuated greatly, the situation that the reading amount is large and more forwarding behaviors cannot be brought is shown, and the fact that the topic popularity is measured by the absolute reading amount of the topic is unreasonable.
In addition, the embodiment of the invention also analyzes the change condition of the total forwarding amount of the microblog platform, and finds that although different hot topics exist on the microblog platform every day, the total forwarding amount of the users does not fluctuate greatly, which is probably because the total time of all the users using the microblog every day is relatively fixed, and although the topics of each day are different, the total forwarding amount is basically unchanged. Based on the premise, each topic has the phenomenon of competing the forwarding behavior of the user. Therefore, it is more reasonable for forwarding prediction to measure the popularity of the topic's reads as a proportion of the total reads.
Based on the analysis, the embodiment of the invention provides a microblog topic popularity quantification method based on attention competition among topics. The total forwarding amount of the microblog platform every day is assumed to be unchanged, and the heat of the topic is the proportion of the reading amount of the topic in the day to the total reading amount of all topics in the day. To simplify the calculation process, the total topic reading amount is approximately represented by the sum of the reading amounts of the top1000 topics ranked the current day. The microblog topic popularity quantification method comprises the following steps:
1. continuously collecting the reading number of the most popular 1000 topics every day, calculating the reading number increased on each topic every day, and recording as ReadTop [ i, j ], wherein the reading number represents the reading number of the topic j on the ith day;
2. sequencing all topics according to reading amount;
3. the total amount of the hottest 1000 topic readings in the day is calculated,
Read[i]the total reading amount of the topic on the day i;
4. topic j on day i, with heat:
5. ordering the topics according to the heat degree;
according to the embodiment of the invention, the hot topics of the Singapore microblog and the reading values of the Singapore microblog are continuously collected every day according to the steps, so that a real-time microblog hot topic table is obtained.
Second, microblog popularity quantification algorithm
According to the embodiment of the invention, the heat of any microblog is quantitatively evaluated based on the topic heat. The basic idea is to compare the contents of the microblog with various topics and measure the popularity of the microblog according to the relevance between the contents of the microblog and the contents of the topics and the popularity of the topics. This faces the semantic expansion problem of topics, among other things. The topic form of the microblog is generally a phrase, which is a summary and abstraction of related contents and cannot be understood only from the literal face of the topic. The main reason for this is that the topic is limited in length, and related contents are abstracted and summarized, so to analyze the relevance of microblog contents and the topic, we should first expand the semantics of the topic. The method comprises the steps of collecting 100 microblogs under a topic (each topic in the microblogs has a microblog list related to the topic), carrying out Chinese word segmentation [ note ] on the microblogs, removing stop words, calculating TF-IDF values of the rest words, considering the words with the top rank as keywords closely related to the topic, and taking the top k words as an expansion word set of the topic and marking as T [ i, j ].
It should be noted that, since the semantic extension of a topic usually does not change much, all semantic expansion work on the topic only needs to be performed once when the topic is collected, and there is no need to repeat calculation every day.
The next step is to calculate the relevance of the microblog content to each topic, and the relevance is a continuous value on [0,1 ]. 0 represents complete irrelevance and 1 represents complete correlation. Employed herein is a cosine algorithm that will be based on a spatial vector. For any one microblog w, the similarity of the microblog w and the topic h is calculated. First, if the topics are completely contained in w, the similarity between the two is 1. Otherwise, segmenting the words of w, constructing a word vector Vw after removing stop words, constructing a word vector Vh according to the topics and the expansion word sets, and calculating the cosine included angle of the two words as the similarity of w and h. The product of the similarity and the heat of the topic h is the heat of w relative to the topic h.
Because one microblog is possibly related to a plurality of topics, the microblog needs to be compared with the top100 hot topics, and the final hot degree of the microblog is obtained after the hot degrees of all the topics are accumulated. Heat _ w, the specific algorithm is shown in table 1:
TABLE 1
Third, forwarding prediction method
After the calculation, a quantitative value related to the hot degree of the microblog content is obtained, and the quantitative value is a relative numerical value and reflects the attraction of the microblog content to the user compared with other microblogs which are spread at the same time. What is exactly the relationship between that value and its probability of being forwarded? We performed a quantitative analysis of this: calculating the popularity of each microblog in the obtained forwarding sample data and neglected sample data, and then analyzing the relation between the popularity of the microblog and the forwarding probability, as shown in fig. 2. As can be seen from fig. 2, in general, the greater the microblog hotness value, the greater the probability that it will be forwarded by the user. When the popularity is 0, the microblog is not related to the current public opinion hotspot, and a certain forwarding probability still exists, because the microblog popularity is only an important factor of forwarding, but not all. There are other factors that affect the user forwarding, such as user relationship, user influence, etc., and when these factors are sufficient, the microblog is prompted to be forwarded even if the degree of heat is 0. This indicates that there is a positive correlation between the microblog popularity and the forwarding probability.
Further, whether the microblog hotness is an effective characteristic for distinguishing forwarding/ignoring is researched, and a cumulative probability Distribution function CDF (cumulative Distribution function) curve graph of the microblog hotness relative to forwarding and ignoring is drawn in the embodiment of the invention. Whether the microblog popularity can effectively distinguish forwarding and ignoring actions can be seen through the forms of the microblog popularity and the microblog popularity. In fig. 3, the distances of forwarding curves and ignoring curves in most microblog hotness intervals are far, which shows that the microblog hotness can effectively distinguish forwarding actions from ignoring actions.
The analysis shows that the microblog popularity is an effective characteristic for predicting microblog forwarding. However, the microblog forwarding is not only related to the microblog popularity, but also many other factors can prompt the user to forward the microblog, and many scholars have already performed many successful research works in this respect, and put forward many effective prediction features, such as user influence, forwarding time, relationships among users, and the like, which can be roughly classified into: user characteristics, social characteristics, temporal characteristics, and content characteristics, as detailed in table 1.
TABLE 1
The embodiment of the invention refers to the characteristics as Basic Features (Basic Features), and the microblog popularity and the Basic Features are combined to carry out forwarding prediction.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A microblog forwarding prediction method based on quantification of popularity is characterized by comprising the following steps:
under the condition that the total daily forwarding amount of the microblog platform is not changed, determining the heat degree of each topic according to the proportion of the daily reading amount of each topic to the total daily reading amount of all topics, and sequencing microblog topics based on the heat degree of the topics to obtain a real-time microblog hot topic table;
comparing the microblog content with the first N microblog topics in the microblog hot topic list, determining the hot degree of the microblog content and the microblog topics according to the correlation between the microblog content and the topic content, and accumulating the hot degree of the microblog content relative to each topic to obtain the final microblog hot degree;
predicting microblog forwarding according to the microblog popularity and the basic characteristics;
comparing the microblog content with the first N microblog topics in the microblog hot topic table, determining the hot degree of the microblog content and the microblog topics according to the correlation between the microblog content and the topic content, and accumulating the hot degree of the microblog content relative to each topic to obtain the final hot degree of the microblog specifically comprises:
when a microblog topic is collected, collecting Q microblogs under the microblog topic, carrying out Chinese word segmentation on the microblogs, removing stop words, calculating TF-IDF values of the rest words, taking the words with the top rank as keywords closely related to the topic, and taking the first K words as an expansion word set of the topic;
for any one microblog w, if the complete topic contained in the w is 1, determining that the similarity of the two is 1, otherwise, segmenting the w, removing stop words, constructing a word vector Vw, constructing a word vector Vh according to the topic and the expansion word set, calculating the cosine included angle of the two and taking the cosine included angle as the similarity of the w and the microblog topic h; calculating the product of the similarity and the heat of the microblog topic h, and taking the product as the heat of w relative to the topic h;
and accumulating the popularity of the microblog to the N hot topics before ranking to obtain the popularity of the final microblog.
2. The method of claim 1, wherein the total number of all topic reads is the sum of the read numbers of M topics before the current rank of the microblog topic.
3. The method of claim 2, wherein under the condition that the total forwarding amount of the microblog platform per day is assumed to be unchanged, determining the hotness of each topic according to the proportion of the reading amount of each topic in the current day to the total reading amount of all topics in the current day, and sequencing microblog topics based on the hotness of the topics to obtain a real-time microblog hotness topic table specifically comprises:
continuously collecting the reading numbers of the most popular M topics every day, calculating the reading numbers increased on each topic every day, and recording as ReadTop [ i, j ], wherein the reading numbers of the topic j on the ith day are represented;
sequencing all topics according to reading amount;
calculating the total reading amount of the hottest M topics in the day according to a formula 1:
wherein Read [ i ] is the topic reading total amount of the ith day;
calculating the heat of topic j on the ith day according to formula 2:
and sequencing the topics according to the heat degree according to the calculation result of the formula 2 to obtain a real-time microblog hot topic list.
4. The method according to claim 1, characterized in that said basic features comprise in particular: user features, social features, temporal features, and content features.
5. A microblog forwarding prediction device based on quantification of popularity is characterized by comprising: memory, processor and computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910119276.4A CN109885656B (en) | 2019-02-18 | 2019-02-18 | Microblog forwarding prediction method and device based on quantification heat degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910119276.4A CN109885656B (en) | 2019-02-18 | 2019-02-18 | Microblog forwarding prediction method and device based on quantification heat degree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109885656A CN109885656A (en) | 2019-06-14 |
| CN109885656B true CN109885656B (en) | 2021-06-29 |
Family
ID=66928179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910119276.4A Active CN109885656B (en) | 2019-02-18 | 2019-02-18 | Microblog forwarding prediction method and device based on quantification heat degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109885656B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222909A (en) * | 2019-06-20 | 2019-09-10 | 郑州工程技术学院 | A kind of dissemination of news force prediction method |
| CN110263254A (en) * | 2019-06-20 | 2019-09-20 | 北京百度网讯科技有限公司 | Event stage division, device, equipment and medium |
| CN110472013B (en) * | 2019-08-06 | 2023-03-24 | 湖南蚁坊软件股份有限公司 | Hot topic updating method and device and computer storage medium |
| CN110598151B (en) * | 2019-09-09 | 2023-07-14 | 河南牧业经济学院 | Method and system for judging news spreading effect |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116605A (en) * | 2013-01-17 | 2013-05-22 | 上海交通大学 | Method and system of microblog hot events real-time detection based on detection subnet |
| CN107122481A (en) * | 2017-05-04 | 2017-09-01 | 成都华栖云科技有限公司 | News temperature real-time online Forecasting Methodology |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103853711B (en) * | 2012-11-28 | 2017-02-08 | 中国移动通信集团广西有限公司 | Text information processing method and device |
| CN104933622A (en) * | 2015-03-12 | 2015-09-23 | 中国科学院计算技术研究所 | Microblog popularity degree prediction method based on user and microblog theme and microblog popularity degree prediction system based on user and microblog theme |
| CN107798027B (en) * | 2016-09-06 | 2021-06-11 | 腾讯科技（深圳）有限公司 | Information popularity prediction method, information recommendation method and device |
| CN106600071A (en) * | 2016-12-20 | 2017-04-26 | 西南石油大学 | Topic-based microblog forwarding prediction method and system |
-
2019
- 2019-02-18 CN CN201910119276.4A patent/CN109885656B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103116605A (en) * | 2013-01-17 | 2013-05-22 | 上海交通大学 | Method and system of microblog hot events real-time detection based on detection subnet |
| CN107122481A (en) * | 2017-05-04 | 2017-09-01 | 成都华栖云科技有限公司 | News temperature real-time online Forecasting Methodology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109885656A (en) | 2019-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109885656B (en) | Microblog forwarding prediction method and device based on quantification heat degree | |
| KR100544514B1 (en) | Method and system for determining relation between search terms in the internet search system | |
| CN107943905B (en) | Hot topic analysis method and system | |
| Paltoglou | Sentiment‐based event detection in T witter | |
| JP4797069B2 (en) | Keyword management program, keyword management system, and keyword management method | |
| US9245035B2 (en) | Information processing system, information processing method, program, and non-transitory information storage medium | |
| JP2015524962A (en) | System and method for automatically generating information-rich content from multiple microblogs, each microblog containing only sparse information | |
| US20120066359A1 (en) | Method and system for evaluating link-hosting webpages | |
| CN104615627B (en) | A kind of event public feelings information extracting method and system based on microblog | |
| CN108874812B (en) | Data processing method, server and computer storage medium | |
| US20130198240A1 (en) | Social Network Analysis | |
| Rong et al. | A model-free approach to infer the diffusion network from event cascade | |
| Fujiki et al. | Identification of bursts in a document stream | |
| Miao et al. | Cost-effective online trending topic detection and popularity prediction in microblogging | |
| JP5952711B2 (en) | Prediction server, program and method for predicting future number of comments in prediction target content | |
| JP5952756B2 (en) | Prediction server, program and method for predicting future number of comments in prediction target content | |
| Dey et al. | Literature survey on interplay of topics, information diffusion and connections on social networks | |
| CN103823847A (en) | Keyword extension method and device | |
| CN114491232B (en) | Information query method and device, electronic equipment and storage medium | |
| WO2022267325A1 (en) | News popularity calculation method, device and storage medium | |
| Hong et al. | Exploiting topic tracking in real-time tweet streams | |
| CN112202889B (en) | Information pushing method, device and storage medium | |
| Wang et al. | Adaptive identification of hashtags for real-time event data collection | |
| Li et al. | Discovering associations between news and contents in social network sites with the D-Miner service framework | |
| Li et al. | Study on topic intensity evolution law of web news topic based on topic content evolution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |