CN115759088A - Text analysis method and storage medium for comment information - Google Patents

Text analysis method and storage medium for comment information Download PDF

Info

Publication number
CN115759088A
CN115759088A CN202310033845.XA CN202310033845A CN115759088A CN 115759088 A CN115759088 A CN 115759088A CN 202310033845 A CN202310033845 A CN 202310033845A CN 115759088 A CN115759088 A CN 115759088A
Authority
CN
China
Prior art keywords
text
gate
output
data
analysis method
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.)
Pending
Application number
CN202310033845.XA
Other languages
Chinese (zh)
Inventor
赵习枝
王苑
张福浩
欧尔格力
仇阿根
张朝坤
李彬
索菲
朱鹏
陶坤旺
陆文
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.)
Qinghai Province Geospatial And Natural Resources Big Data Center
Chinese Academy of Surveying and Mapping
Original Assignee
Qinghai Province Geospatial And Natural Resources Big Data Center
Chinese Academy of Surveying and Mapping
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
Application filed by Qinghai Province Geospatial And Natural Resources Big Data Center, Chinese Academy of Surveying and Mapping filed Critical Qinghai Province Geospatial And Natural Resources Big Data Center
Priority to CN202310033845.XA priority Critical patent/CN115759088A/en
Publication of CN115759088A publication Critical patent/CN115759088A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

A text analysis method for comment information and a storage medium thereof are disclosed, firstly, text comment data are preprocessed, text feature vectors are obtained by text vectorization on the preprocessed data, data noise reduction is carried out by using a self-encoder model, and then high-level feature vectors of the text comment information are extracted through a long-term and short-term memory network, so that text analysis of the comment information is realized. According to the invention, the data is subjected to noise reduction processing through the AE model, redundant features in the data are eliminated, and the efficiency of comment information analysis is effectively improved; by adopting the LSTM model, the document information is effectively utilized, so that the characteristics are more judgment, and the accuracy of comment information analysis is improved.

Description

Text analysis method and storage medium for comment information
Technical Field
The invention relates to the technical field of natural language processing, in particular to a text analysis method and a storage medium for comment information.
Background
With the development of internet technology, social media platforms become an important way for the public to publish opinions and communicate information. A large amount of social media comment data are collected from the Internet, valuable information in the social media comment data is mined, and the like of the people on the preference degree of a certain product or the attention degree and emotional change of a certain social phenomenon can be obtained.
Because social media websites are various in types and have too large amount of comment information, the arrangement and analysis of the comment information only by manpower can be a difficult task, so that the text comment information analysis needs to be further explored, complicated language features are automatically learned from a large amount of text data by adopting a more automatic and intelligent method and the text analysis is carried out, a large amount of manpower and material resources are saved, and the text comment analysis efficiency and accuracy are improved.
Disclosure of Invention
The invention aims to provide a text comment analysis method aiming at the problems of low efficiency, large workload, low accuracy and the like in the working mode of manual text comment analysis, so as to solve the problems.
In order to achieve the purpose, the invention adopts the following technical scheme:
a text analysis method of comment information comprises the following steps:
text comment data preprocessing step S110:
preprocessing the text comment data, filtering out irrelevant information, and performing word segmentation processing on the text comment data;
text comment vector extraction and processing step S120:
text feature vectors are obtained by text vectorization of the preprocessed text comment data, data noise reduction is carried out by using a self-encoder model, and then high-level feature vectors of text comment information are extracted through an LSTM model to represent the text comment data;
calculating emotion prediction results of the text comments S130:
receiving the high-level feature vector of the text comment information extracted in step S120, and calculating an emotion prediction result of the text comment.
Optionally, in step S110, the text comment data preprocessing specifically includes: and deleting punctuation marks and blank spaces by adopting a regular expression, introducing a field dictionary into the text data, and performing word segmentation processing on the data.
Optionally, in step S120, the self-encoder model is an unsupervised learning model, which can eliminate redundant features in data, reduce noise in data, and improve efficiency of comment information analysis.
The output vector of the self-encoder model
Figure 339397DEST_PATH_IMAGE001
The calculation formula is as follows:
Figure 537423DEST_PATH_IMAGE002
wherein, the first and the second end of the pipe are connected with each other,
Figure 634692DEST_PATH_IMAGE003
in order to be a function of the ReLU,
Figure 201939DEST_PATH_IMAGE004
in order to input the feature vector of the text,
Figure 359251DEST_PATH_IMAGE005
to represent
Figure 74266DEST_PATH_IMAGE006
The weight matrix of (a) is determined,
Figure 709647DEST_PATH_IMAGE007
is composed of
Figure 131401DEST_PATH_IMAGE004
The bias term of (d);
optionally, in step S120, the LSTM model is a bidirectional improved recurrent neural network, and a bidirectional coding structure with stronger semantic ability is used to train the corpus, so as to implement deep bidirectional representation of corpus training.
Optionally, in step S120, the LSTM model is composed of 3 gate structures and 1 state unit, where the 3 gate structures include an input gate, a forgetting gate, and an output gate;
wherein the input gate receives two inputs, the output of the last-in-time LSTM model
Figure 754887DEST_PATH_IMAGE008
And input of the current time
Figure 894881DEST_PATH_IMAGE001
Output of input gate at time t
Figure 599532DEST_PATH_IMAGE009
The calculation formula is as follows:
Figure 875793DEST_PATH_IMAGE010
wherein the content of the first and second substances,
Figure 374907DEST_PATH_IMAGE011
in order to be a sigmoid function,
Figure 2198DEST_PATH_IMAGE012
a weight matrix representing the input gate,
Figure 979381DEST_PATH_IMAGE013
indicating that two vectors are concatenated into one longer vector,
Figure 142771DEST_PATH_IMAGE014
is the bias term of the input gate;
output of the forgetting gate
Figure 812787DEST_PATH_IMAGE015
Also receiving the output result of the last time LSTM model
Figure 724111DEST_PATH_IMAGE008
And input of the current time
Figure 504985DEST_PATH_IMAGE001
And determining whether to discard information from the state unit, the output calculation formula is:
Figure 21417DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure 862334DEST_PATH_IMAGE011
is a function of the sigmoid and is,
Figure 464217DEST_PATH_IMAGE017
is a weight matrix of the forgetting gate,
Figure 299316DEST_PATH_IMAGE018
meaning that two vectors are concatenated into one longer vector,
Figure 670255DEST_PATH_IMAGE019
is a biased term for a forgetting gate.
Instantaneous state cell value at current time
Figure 682073DEST_PATH_IMAGE020
Expressed as:
Figure 505673DEST_PATH_IMAGE021
wherein the content of the first and second substances,
Figure 690666DEST_PATH_IMAGE022
is that
Figure 916111DEST_PATH_IMAGE020
The weight matrix of (a) is determined,
Figure 98831DEST_PATH_IMAGE018
representing the concatenation of two vectors into one longer vector, tanh represents the hyperbolic tangent activation function,
Figure 176771DEST_PATH_IMAGE023
is that
Figure 103138DEST_PATH_IMAGE020
The bias term of (c).
The status cell at the current time
Figure 183090DEST_PATH_IMAGE024
Receiving values for the input gate and the forget gate, expressed as:
Figure 536711DEST_PATH_IMAGE025
wherein, the first and the second end of the pipe are connected with each other,
Figure 334902DEST_PATH_IMAGE026
the cell state at the previous time is initialized to 1.
Output gate
Figure 799382DEST_PATH_IMAGE027
For controlling the output of the LSTM state unit, the expression:
Figure 999419DEST_PATH_IMAGE028
wherein, the first and the second end of the pipe are connected with each other,
Figure 84793DEST_PATH_IMAGE011
is a function of the sigmoid and is,
Figure 104702DEST_PATH_IMAGE029
is a weight matrix of the output gates,
Figure 638451DEST_PATH_IMAGE018
meaning that two vectors are concatenated into one longer vector,
Figure 692995DEST_PATH_IMAGE030
is the bias term for the output gate.
Finally, outputting the state unit of the LSTM model at the current moment
Figure 388419DEST_PATH_IMAGE031
Expressed as:
Figure 161202DEST_PATH_IMAGE032
。
optionally, in step S130, an output of the LSTM model, which is a high-level feature vector of the text comment information extracted in step S120, is received
Figure 233064DEST_PATH_IMAGE031
Obtaining emotion prediction result of text comment through softmax function
Figure 142114DEST_PATH_IMAGE033
The calculation formula is as follows:
Figure 775483DEST_PATH_IMAGE034
wherein the content of the first and second substances,
Figure 504404DEST_PATH_IMAGE011
is a function of the sigmoid and is,
Figure 379956DEST_PATH_IMAGE035
is an emotion prediction result
Figure 409092DEST_PATH_IMAGE033
The weight matrix of (a) is determined,
Figure 446319DEST_PATH_IMAGE036
is an emotion prediction result
Figure 193695DEST_PATH_IMAGE033
The bias term of (c). When the temperature is higher than the set temperature
Figure 404096DEST_PATH_IMAGE037
When so, the emotion prediction is positive.
Further, the present invention also discloses a storage medium for storing computer-executable instructions, which, when executed by a processor, perform the above-mentioned text analysis method for comment information.
Compared with the prior art, the invention has the following advantages:
1) Because the AE model is adopted for data noise reduction, redundant features in data can be eliminated, and text analysis efficiency of comment information is improved.
2) The invention adopts the LSTM model and effectively utilizes the document information, thereby enabling the characteristics to be more judgment and improving the accuracy of text analysis of comment information.
Drawings
Fig. 1 is a flowchart of a text analysis method of comment information according to a specific embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
The invention is characterized in that: and (3) carrying out data noise reduction by using an automatic encoder model (AE model), eliminating redundant features in the data, and extracting a high-level feature vector of the text comment information by using an LSTM model to realize text analysis of the comment information.
Referring to fig. 1, a flowchart of a text analysis method of comment information according to an embodiment of the present invention is shown, including the following steps:
text comment data preprocessing step S110:
and preprocessing the text comment data, filtering out irrelevant information, and performing word segmentation processing on the text comment data.
Specifically, in step S110, the text comment data preprocessing specifically includes: and deleting punctuation marks and blank spaces by adopting a regular expression, introducing a field dictionary into the text data, and performing word segmentation processing on the data.
Text comment vector extraction and processing step S120:
and for the preprocessed text comment data, text feature vectors are obtained by text vectorization, data noise reduction is carried out by using an Auto-Encoder model (Auto-Encoder), and then high-level feature vectors of text comment information are extracted through a Long Short-Term Memory network (LSTM) model to represent the text comment data.
Specifically, in step S120, the self-encoder model is an unsupervised learning model, which can eliminate redundant features in data, reduce noise in data, and improve efficiency of comment information analysis.
The output vector of the self-encoder model
Figure 792133DEST_PATH_IMAGE001
The calculation formula is as follows:
Figure 260DEST_PATH_IMAGE002
wherein the content of the first and second substances,
Figure 969353DEST_PATH_IMAGE003
in order to be a function of the ReLU,
Figure 186708DEST_PATH_IMAGE004
for the feature vector of the text to be input,
Figure 924857DEST_PATH_IMAGE005
represent
Figure 303886DEST_PATH_IMAGE004
The weight matrix of (a) is determined,
Figure 760275DEST_PATH_IMAGE007
is composed of
Figure 515741DEST_PATH_IMAGE004
The bias term of (c).
The LSTM model is a bidirectional improved recurrent neural network, and a bidirectional coding structure with stronger semantic ability is adopted to train the corpus so as to realize deep bidirectional representation of corpus training.
Specifically, in step S120, the LSTM model is composed of 3 gate structures and 1 state unit, where the 3 gate structures include an input gate, a forgetting gate, and an output gate;
wherein the input gate receives two inputs, the output of the last-in LSTM model
Figure 875441DEST_PATH_IMAGE008
And input of the current time
Figure 690950DEST_PATH_IMAGE001
Output of input gate at time t
Figure 165794DEST_PATH_IMAGE009
The calculation formula is as follows:
Figure 724951DEST_PATH_IMAGE010
wherein, the first and the second end of the pipe are connected with each other,
Figure 437692DEST_PATH_IMAGE011
in order to be a sigmoid function,
Figure 424103DEST_PATH_IMAGE012
a weight matrix representing the input gate,
Figure 855084DEST_PATH_IMAGE013
meaning that two vectors are concatenated into one longer vector,
Figure 450888DEST_PATH_IMAGE014
is the bias term of the input gate;
output of the forgetting gate
Figure 18136DEST_PATH_IMAGE015
Also receiving the output result of the last time LSTM model
Figure 175448DEST_PATH_IMAGE008
And input of the current time
Figure 828146DEST_PATH_IMAGE001
And determining whether to discard information from the state unit, the output calculation formula is:
Figure 729106DEST_PATH_IMAGE016
wherein, the first and the second end of the pipe are connected with each other,
Figure 416439DEST_PATH_IMAGE011
is a function of the sigmoid and is,
Figure 479073DEST_PATH_IMAGE017
is a weight matrix of the forgetting gate,
Figure 917270DEST_PATH_IMAGE018
meaning that two vectors are concatenated into one longer vector,
Figure 90762DEST_PATH_IMAGE019
is a biased term for a forgetting gate.
Instantaneous state cell value at current time
Figure 632602DEST_PATH_IMAGE020
Expressed as:
Figure 928454DEST_PATH_IMAGE021
wherein the content of the first and second substances,
Figure 555744DEST_PATH_IMAGE022
is that
Figure 798507DEST_PATH_IMAGE020
The weight matrix of (a) is determined,
Figure 460432DEST_PATH_IMAGE018
representing the concatenation of two vectors into one longer vector, tanh represents the hyperbolic tangent activation function,
Figure 357545DEST_PATH_IMAGE023
is that
Figure 206552DEST_PATH_IMAGE020
The bias term of (1).
The status cell at the current time
Figure 253006DEST_PATH_IMAGE024
Receiving values for the input gate and the forget gate, expressed as:
Figure 769437DEST_PATH_IMAGE025
wherein the content of the first and second substances,
Figure 610355DEST_PATH_IMAGE026
the cell state at the previous time is initialized to 1.
Output gate
Figure 743396DEST_PATH_IMAGE027
For controlling the output of the LSTM state unit, the expression:
Figure 327961DEST_PATH_IMAGE028
wherein the content of the first and second substances,
Figure 200364DEST_PATH_IMAGE011
is a function of the sigmoid and is,
Figure 212182DEST_PATH_IMAGE029
is a weight matrix of the output gates,
Figure 301361DEST_PATH_IMAGE018
indicating that two vectors are concatenated into one longer vector,
Figure 424038DEST_PATH_IMAGE030
is the bias term for the output gate.
Finally, outputting the state unit of the LSTM model at the current moment
Figure 915062DEST_PATH_IMAGE031
Expressed as:
Figure 832203DEST_PATH_IMAGE032
。
calculating emotion prediction results of the text comments S130:
receiving the high-level feature vector of the text comment information extracted in step S120, and calculating an emotion prediction result of the text comment.
Specifically, in step S130, the input of the LSTM model, which is the high-level feature vector of the text comment information extracted in step S120, is receivedGo out
Figure 143098DEST_PATH_IMAGE031
Obtaining emotion prediction result of text comment through softmax function
Figure 69466DEST_PATH_IMAGE033
The calculation formula is as follows:
Figure 913532DEST_PATH_IMAGE034
wherein the content of the first and second substances,
Figure 63890DEST_PATH_IMAGE011
is a function of the sigmoid and is,
Figure 862082DEST_PATH_IMAGE035
is an emotion prediction result
Figure 592141DEST_PATH_IMAGE033
The weight matrix of (a) is determined,
Figure 792178DEST_PATH_IMAGE036
is an emotion prediction result
Figure 51121DEST_PATH_IMAGE033
The bias term of (c).
When in use
Figure 336609DEST_PATH_IMAGE037
Then, the emotion prediction is positive.
Further, the present invention also discloses a storage medium for storing computer-executable instructions, which, when executed by a processor, perform the above-mentioned text analysis method of comment information.
Compared with the prior art, the text analysis method of the comment information provided by the invention has the following advantages:
1) According to the invention, the AE model is adopted for data noise reduction, so that redundant features in the data can be eliminated, and the text analysis efficiency of comment information is improved.
2) The invention adopts the LSTM model and effectively utilizes the document information, thereby enabling the characteristics to be more judgment and improving the accuracy of text analysis of comment information.
It will be apparent to those skilled in the art that the various elements or steps of the invention described above may be implemented using a general purpose computing device, they may be centralized on a single computing device, or alternatively, they may be implemented using program code that is executable by a computing device, such that they may be stored in a memory device and executed by a computing device, or they may be separately fabricated into various 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.
While the invention has been described in further detail with reference to specific preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (8)

1. A text analysis method for comment information is characterized by comprising the following steps:
text comment data preprocessing step S110:
preprocessing the text comment data, filtering out irrelevant information, and performing word segmentation processing on the text comment data;
text comment vector extraction and processing step S120:
text feature vectors are obtained by text vectorization on the preprocessed text comment data, data noise reduction is carried out by using a self-encoder model, and then high-level feature vectors of text comment information are extracted through an LSTM model to represent the text comment data;
calculating emotion prediction results of the text comments S130:
receiving the high-level feature vector of the text comment information extracted in step S120, and calculating an emotion prediction result of the text comment.
2. The text analysis method according to claim 1, wherein:
in step S110, the text comment data preprocessing specifically includes: and deleting punctuation marks and blank spaces by adopting a regular expression, introducing a field dictionary into the text data, and performing word segmentation processing on the data.
3. The text analysis method of claim 1, wherein:
in step S120, the self-encoder model is an unsupervised learning model,
the output vector of the self-encoder model
Figure 881980DEST_PATH_IMAGE001
The calculation formula is as follows:
Figure 419272DEST_PATH_IMAGE002
wherein the content of the first and second substances,
Figure 26971DEST_PATH_IMAGE003
in order to be a function of the ReLU,
Figure 344820DEST_PATH_IMAGE004
for the feature vector of the text to be input,
Figure 266639DEST_PATH_IMAGE005
to represent
Figure 983404DEST_PATH_IMAGE006
The weight matrix of (a) is determined,
Figure 965266DEST_PATH_IMAGE007
is composed of
Figure 504832DEST_PATH_IMAGE008
The bias term of (1).
4. The text analysis method of claim 3, wherein:
in step S120, the LSTM model is a bidirectional improved recurrent neural network, and a bidirectional coding structure with a stronger semantic ability is used to train the corpus, so as to implement deep bidirectional representation of corpus training.
5. The text analysis method of claim 4, wherein:
in step S120, the LSTM model is composed of 3 gate structures and 1 state unit, where the 3 gate structures include an input gate, a forgetting gate, and an output gate;
wherein the input gate receives two inputs, the output of the last-in-time LSTM model
Figure 292660DEST_PATH_IMAGE009
And input of the current time
Figure 804543DEST_PATH_IMAGE001
Output of input gate at time t
Figure 754045DEST_PATH_IMAGE010
The calculation formula is as follows:
Figure 780907DEST_PATH_IMAGE011
wherein, the first and the second end of the pipe are connected with each other,
Figure 106846DEST_PATH_IMAGE012
in order to be a sigmoid function,
Figure 473236DEST_PATH_IMAGE013
a weight matrix representing the input gates is shown,
Figure 859218DEST_PATH_IMAGE014
meaning that two vectors are concatenated into one longer vector,
Figure 576639DEST_PATH_IMAGE015
is the bias term of the input gate;
output of the forgetting gate
Figure 706269DEST_PATH_IMAGE016
Also receiving the output result of the last time LSTM model
Figure 918376DEST_PATH_IMAGE009
And input of the current time
Figure 475260DEST_PATH_IMAGE001
And determining whether to discard information from the state unit, the output calculation formula is:
Figure 476714DEST_PATH_IMAGE017
wherein, the first and the second end of the pipe are connected with each other,
Figure 144455DEST_PATH_IMAGE012
is a function of the sigmoid and is,
Figure 219859DEST_PATH_IMAGE018
is a weight matrix of the forgetting gate,
Figure 947643DEST_PATH_IMAGE019
indicating that two vectors are concatenated into one longer vector,
Figure 639656DEST_PATH_IMAGE020
is a biased term for a forgetting gate;
instantaneous state unit value of current time
Figure 845509DEST_PATH_IMAGE021
Expressed as:
Figure 103315DEST_PATH_IMAGE022
wherein, the first and the second end of the pipe are connected with each other,
Figure 205263DEST_PATH_IMAGE023
is that
Figure 915731DEST_PATH_IMAGE024
The weight matrix of (a) is determined,
Figure 925275DEST_PATH_IMAGE019
representing the concatenation of two vectors into one longer vector, tanh represents the hyperbolic tangent activation function,
Figure 237920DEST_PATH_IMAGE025
is that
Figure 41928DEST_PATH_IMAGE021
The bias term of (a);
the status cell at the current time
Figure 505270DEST_PATH_IMAGE026
Receiving values for the input gate and the forget gate, expressed as:
Figure 52926DEST_PATH_IMAGE027
wherein, the first and the second end of the pipe are connected with each other,
Figure 223008DEST_PATH_IMAGE028
the cell state at the previous moment is initialized to 1;
output gate
Figure 463496DEST_PATH_IMAGE029
For controlling the output of the LSTM state unit, the expression:
Figure 148555DEST_PATH_IMAGE030
wherein the content of the first and second substances,
Figure 703165DEST_PATH_IMAGE012
is a function of the sigmoid and is,
Figure 524490DEST_PATH_IMAGE031
is a weight matrix of the output gates,
Figure 201459DEST_PATH_IMAGE019
indicating that two vectors are concatenated into one longer vector,
Figure 108235DEST_PATH_IMAGE032
is the bias term of the output gate;
finally, outputting the state unit of the LSTM model at the current moment
Figure 200956DEST_PATH_IMAGE033
Expressed as:
Figure 145297DEST_PATH_IMAGE034
。
6. the text analysis method of claim 5, wherein:
in step S130, the output of the LSTM model, which is the high-level feature vector of the text comment information extracted in step S120, is received
Figure 727588DEST_PATH_IMAGE033
Obtaining emotion prediction results of text comments through softmax function
Figure 324923DEST_PATH_IMAGE035
The calculation formula is as follows:
Figure 283651DEST_PATH_IMAGE036
wherein the content of the first and second substances,
Figure 282831DEST_PATH_IMAGE012
is a function of the sigmoid and is,
Figure 301603DEST_PATH_IMAGE037
is an emotion prediction result
Figure 182971DEST_PATH_IMAGE035
The weight matrix of (a) is determined,
Figure 617495DEST_PATH_IMAGE038
is an emotion prediction result
Figure 533498DEST_PATH_IMAGE035
The bias term of (1).
7. The text analysis method of claim 6, wherein:
when the temperature is higher than the set temperature
Figure 457592DEST_PATH_IMAGE039
When so, the emotion prediction is positive.
8. A storage medium storing computer-executable instructions, characterized in that:
the computer-executable instructions, when executed by a processor, perform a method of text analysis of review information as recited in any of claims 1-7.
CN202310033845.XA 2023-01-10 2023-01-10 Text analysis method and storage medium for comment information Pending CN115759088A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310033845.XA CN115759088A (en) 2023-01-10 2023-01-10 Text analysis method and storage medium for comment information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310033845.XA CN115759088A (en) 2023-01-10 2023-01-10 Text analysis method and storage medium for comment information

Publications (1)

Publication Number Publication Date
CN115759088A true CN115759088A (en) 2023-03-07

Family

ID=85348879

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310033845.XA Pending CN115759088A (en) 2023-01-10 2023-01-10 Text analysis method and storage medium for comment information

Country Status (1)

Country Link
CN (1) CN115759088A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107153642A (en) * 2017-05-16 2017-09-12 华北电力大学 A kind of analysis method based on neural network recognization text comments Sentiment orientation
CN110737952A (en) * 2019-09-17 2020-01-31 太原理工大学 prediction method for residual life of key parts of mechanical equipment by combining AE and bi-LSTM
CN111127146A (en) * 2019-12-19 2020-05-08 江西财经大学 Information recommendation method and system based on convolutional neural network and noise reduction self-encoder
CN114138942A (en) * 2021-12-09 2022-03-04 南京审计大学 Violation detection method based on text emotional tendency

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107153642A (en) * 2017-05-16 2017-09-12 华北电力大学 A kind of analysis method based on neural network recognization text comments Sentiment orientation
CN110737952A (en) * 2019-09-17 2020-01-31 太原理工大学 prediction method for residual life of key parts of mechanical equipment by combining AE and bi-LSTM
CN111127146A (en) * 2019-12-19 2020-05-08 江西财经大学 Information recommendation method and system based on convolutional neural network and noise reduction self-encoder
CN114138942A (en) * 2021-12-09 2022-03-04 南京审计大学 Violation detection method based on text emotional tendency

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陶志勇等: "基于双向长短时记忆网络的改进注意力短文本分类方法" *

Similar Documents

Publication Publication Date Title
US11631007B2 (en) Method and device for text-enhanced knowledge graph joint representation learning
CN109871451B (en) Method and system for extracting relation of dynamic word vectors
CN110321563B (en) Text emotion analysis method based on hybrid supervision model
CN110717332B (en) News and case similarity calculation method based on asymmetric twin network
CN110210016B (en) Method and system for detecting false news of bilinear neural network based on style guidance
CN110472042B (en) Fine-grained emotion classification method
CN108399241B (en) Emerging hot topic detection system based on multi-class feature fusion
CN104268197A (en) Industry comment data fine grain sentiment analysis method
CN111143563A (en) Text classification method based on integration of BERT, LSTM and CNN
CN111782797A (en) Automatic matching method for scientific and technological project review experts and storage medium
CN113392209B (en) Text clustering method based on artificial intelligence, related equipment and storage medium
CN107688576B (en) Construction and tendency classification method of CNN-SVM model
CN110134788B (en) Microblog release optimization method and system based on text mining
CN111222330B (en) Chinese event detection method and system
CN105975475A (en) Chinese phrase string-based fine-grained thematic information extraction method
WO2023004528A1 (en) Distributed system-based parallel named entity recognition method and apparatus
CN112256866A (en) Text fine-grained emotion analysis method based on deep learning
CN114722820A (en) Chinese entity relation extraction method based on gating mechanism and graph attention network
CN114020906A (en) Chinese medical text information matching method and system based on twin neural network
CN115080750B (en) Weak supervision text classification method, system and device based on fusion prompt sequence
CN112561718A (en) Case microblog evaluation object emotion tendency analysis method based on BilSTM weight sharing
Fu et al. Improving distributed word representation and topic model by word-topic mixture model
CN115759119A (en) Financial text emotion analysis method, system, medium and equipment
CN111090724A (en) Entity extraction method capable of judging relevance between text content and entity based on deep learning
CN111104508B (en) Method, system and medium for representing word bag model text based on fault-tolerant rough set

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20230307