CN113821628A - Method, apparatus, program, and medium for value evaluation using social media short text - Google Patents
Method, apparatus, program, and medium for value evaluation using social media short text Download PDFInfo
- Publication number
- CN113821628A CN113821628A CN202010554827.2A CN202010554827A CN113821628A CN 113821628 A CN113821628 A CN 113821628A CN 202010554827 A CN202010554827 A CN 202010554827A CN 113821628 A CN113821628 A CN 113821628A
- Authority
- CN
- China
- Prior art keywords
- short text
- social
- text
- value
- evaluation
- 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
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004458 analytical method Methods 0.000 claims abstract description 57
- 230000008451 emotion Effects 0.000 claims abstract description 44
- 230000002996 emotional effect Effects 0.000 claims abstract description 38
- 238000012549 training Methods 0.000 claims description 21
- 238000007781 pre-processing Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 235000010627 Phaseolus vulgaris Nutrition 0.000 description 10
- 244000046052 Phaseolus vulgaris Species 0.000 description 10
- 238000012935 Averaging Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000009849 deactivation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/355—Creation or modification of classes or clusters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a method, a device, a program and a medium for value evaluation by using a social short text, which are characterized in that an emotion analysis network is constructed by using a source short text and an evaluation tag thereof, so that the emotional tendency/emotional characteristic of a target short text of a topic object to be evaluated is analyzed, the emotional tendency/emotional characteristic is fused, and an evaluation result is output. In the value evaluation, the characteristics of wide social media audiences and large short text sample amount are fully utilized, and more logical and interpretable value evaluation is provided than other value evaluation methods.
Description
Technical Field
The invention relates to the field of social media data mining and artificial intelligence; and more particularly, to a method and apparatus, a program, and a medium for value evaluation using social media short text.
Background
With the growth of social media, a phenomenon appears that topic objects which are good in taste on the social media, such as a piece of film and television works with excellent public praise and a popular club, are generally considered to be more valuable and are easier to succeed in the market. Due to the strong transmission capability of the social media, the emotional tendency of the audience can be efficiently and widely transmitted through the short text form of the social media such as comments and messages, and further the value of the topic object is influenced and reflected.
Now that such a large amount of short text with varied emotional colors exists on social media. Then, theoretically, the audience likes and dislikes of the specific topic object can be estimated by carrying out emotion analysis on the short text content of the social media and integrating the emotion analysis results.
However, such huge text information is obviously a dream of the people depending on the manual itemization analysis. Then, sentiment analysis (also called opinion mining) by means of a computer is required. The existing text tendency emotion analysis method based on statistics is effective. In the method, a certain amount of marked emotion label texts are required to be used as a training set, and then a model is constructed for emotion analysis.
However, the most abundant short texts are general non-professional comprehensive social media, such as microblog, wechat, etc.; these short texts are obviously devoid of so-called emotion label tags. For short text of this order of magnitude, manual labeling is also not desirable. The problem that social media texts are free of emotion labels is solved by adopting the ready-made emotion semantic word library, and the evaluation result is influenced because the data characteristics of the social media texts are distributed differently due to the fact that the social media texts are related to different themes.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a program, and a medium for value evaluation using short social media text.
In one aspect, the embodiments of the present invention provide a method for social media short text sentiment analysis, which is used for analyzing sentiment tendency in short text (such as comments, messages, etc.) related to some specific topic objects (such as movie and television IP works, literature works, sports clubs, athletes, etc.) on social media.
The social media short text sentiment analysis method comprises the following steps:
acquiring a target short text;
acquiring a source short text and an evaluation label corresponding to the source short text;
training an emotion analysis network by taking the source short text and the evaluation label as a training sample set;
and inputting the target short text into the emotion analysis network obtained by the training, and analyzing the emotion tendency of the target short text.
In another aspect, an embodiment of the present invention provides a method for evaluating value by using a social media short text.
With reference to the first aspect, the value evaluation method based on the social media short text sentiment analysis method includes:
acquiring a social media short text of a topic object to be evaluated;
analyzing the short text of the social media by using the method mentioned in the first aspect, and outputting emotional tendency/emotional characteristic;
and fusing emotional tendency/emotional characteristic of the short text of the social media to evaluate the value of the topic object.
In another aspect, an embodiment of the present invention provides a neural network system.
With reference to the first and second aspects, the neural network system described above includes:
the emotion analysis network obtained by training in the first aspect is used for analyzing emotion characteristics of the input social media short text;
and the fusion layer is used for fusing the emotional characteristics for value evaluation.
In another aspect, an embodiment of the present invention provides an apparatus for evaluating value by using short social media texts.
With reference to the first, second, and third aspects, the value evaluation device described above includes:
the input unit is used for acquiring a social media short text of a topic object to be evaluated;
an evaluation unit configured to implement the value evaluation method according to the second aspect, and evaluate the value of the topic object; the method comprises the steps of training an obtained emotion analysis network by the method mentioned in the first aspect, analyzing the short text, outputting emotional tendency/emotional characteristic, and fusing the emotional tendency/emotional characteristic to evaluate the value of the topic object;
and the output unit is used for outputting the evaluation result, namely the value of the topic object to be evaluated obtained by the evaluation.
In another aspect, the embodiment of the invention provides a device for social media short text sentiment analysis.
With reference to the first, second, third, and fourth aspects, the short text emotion analyzing apparatus includes:
the input unit is used for acquiring a target short text;
an analysis unit, which comprises the emotion analysis network obtained by training in the first aspect and the method; the target short text is analyzed;
and the output unit is used for outputting the analysis result.
In another aspect, an embodiment of the present invention provides an electronic device.
With reference to the first, second, and third aspects, correspondingly, the electronic device includes:
a memory and a processor;
the memory is used for storing executable instructions;
the processor is used for communicating with the memory to execute the stored executable instructions so as to complete the operations of the method for emotion analysis of the social media short text in any one of the first aspect and/or the method for value evaluation by using the social media short text in any one of the second aspect.
In another aspect, an embodiment of the present invention provides an electronic device.
With reference to the fourth and fifth aspects, correspondingly, the electronic device includes:
a processor;
the processor comprises a value evaluation device as set forth in any one of the fourth aspects and/or a short text sentiment analysis device as set forth in any one of the fifth aspects.
In yet another aspect, an embodiment of the present invention provides a computer program product.
With reference to the first and second aspects, the computer program product includes:
computer readable code;
the computer readable code, when executed on a device, causes a processor in the device to execute instructions for implementing the method for sentiment analysis of social media short text recited in any one of the first aspects and/or the method for value assessment using social media short text recited in any one of the second aspects.
In yet another aspect, an embodiment of the present invention provides a computer-readable storage medium.
With reference to the first and second aspects, the computer-readable storage medium is configured to store computer-readable instructions;
the instructions when executed perform the operations of the method for emotion analysis of the social media short text in any one of the first aspects and/or the method for value evaluation by using the social media short text in any one of the second aspects.
According to the technical scheme provided by each embodiment of the invention, the emotion analysis network is constructed by utilizing the source short text and the evaluation tag thereof, so that the emotional tendency/emotional characteristic of the target short text of the topic object to be evaluated is analyzed, the emotional tendency/emotional characteristic is fused, and the evaluation result is output. In the value evaluation, the characteristics of wide social media audiences and large short text sample amount are fully utilized, and more logical and interpretable value evaluation is provided than other value evaluation methods.
The technical solution of the present invention is further described with reference to the accompanying drawings and specific embodiments.
Drawings
To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings related to a part of the embodiments of the present invention or the description in the prior art will be briefly introduced below.
Fig. 1 is a flowchart illustrating a method for value evaluation using social media short text according to some embodiments of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention is clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the described embodiments are merely exemplary of a portion of the invention and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
The following are some preferred embodiments of the invention. Wherein,
some of the above preferred embodiments provide a method for social media short text sentiment analysis for analyzing sentiment tendencies in short text (e.g., comments, messages, etc.) on social media that relate to certain topic objects (e.g., movie IP works, literary works, sports clubs, athletes, etc.).
The social media short text sentiment analysis method comprises the following steps:
acquiring a target short text; the method comprises the steps of acquiring any short text from a social media and related to a certain topic object, such as a message discussed on a microblog and a message of evaluating a movie and television play, and taking the short text as an analysis object;
since some social media such as microblog are taken as a comprehensive social media, the target short text has no quantitative and machine-recognizable emotion tag, so that the source short text and the corresponding evaluation tag are obtained from another source media (usually professional media, such media can give evaluation marks in addition to the short text evaluation); specifically, the topic object and/or the social media short text (namely, the source short text) of the topic object of the same type as the topic object (such as other movie works when the topic object is a movie, other football clubs when the topic object is a football club, etc.) on the source media and the evaluation label corresponding to the source short text are sampled; taking the source short text and the evaluation labels as training sample sets, and training an emotion analysis network by adopting a supervised learning mode;
and inputting the target short text into an emotion analysis network obtained by training, so that the emotion tendency of the target short text can be analyzed and output.
In some of the above embodiments, the target short text and the source text are subjected to text preprocessing before being input, analyzed and trained, so that the accuracy of analysis is improved. The preprocessing can include word segmentation, word deactivation, keyword extraction, one hot encoding/word 2vector and the like.
FIG. 1 is a flow chart illustrating another method for value assessment using social media short text in accordance with the preferred embodiments described above. As shown in figure 1 of the drawings, in which,
the method comprises the following steps:
acquiring a social media short text of a topic object to be evaluated;
analyzing the social media short text by the method in the embodiment, and outputting emotional tendency/emotional characteristic; in particular, the method comprises the following steps of,
acquiring a source short text and an evaluation label of a topic object to be evaluated on a source medium, and training an emotion analysis network; inputting the social media short texts of the topic objects to be evaluated into the emotion analysis network, and analyzing and outputting emotional tendency/emotional characteristics;
fusing emotional tendency/emotional characteristics of the social media short texts to evaluate the value of the topic object; specifically, the fusion may be to average the emotional tendency/emotional characteristic described above as the result of evaluating the value, and more preferably, to adopt a weighted average, which is a preferred embodiment that a higher weight is given to the high-value user according to the user rating of making short text evaluation/leaving message, so as to reduce the behavior of swiping a chart of "water army" and the like and to evaluate the interference of the result.
The following is a specific example in the above preferred embodiment, namely, the quality of the drama "happy palace book" is evaluated by leaving a microblog message, and the process is as follows:
1) obtaining microblog messages of "Yanxi Gong Miao":
crawl microblog messages of 'Yanxi Gong Mi' (such as 'Yanxi Gong Mi' (a tiny user message of 'Yanxi Gong Mi');
2) obtaining bean paste data:
acquiring the bean short comment of the bean and star grade corresponding to the bean short comment of the bean in "Yanxigong Miao" and similar works (in the bean, the network is classified as TV drama); sampling under the program of the bean drama, wherein the bean short scores and star grades of 3000 dramas are sampled to be used as source short texts and evaluation labels;
3) text pre-processing
Carrying out word segmentation and word stop removal on the microblog messages and the bean short comments one by one, and particularly further carrying out preprocessing of extracting keywords and word2 vector;
4) training emotion analysis networks
The bean short-term scores and star-grade scores after text preprocessing are used as training sample sets, and an emotion analysis network is trained in a supervised learning mode;
5) analyzing microblog message emotion
Inputting the microblog messages after text preprocessing into the emotion analysis network, and analyzing and outputting emotion tendencies of the microblog messages;
6) fusion assessment
Carrying out weighted average on the emotional tendency, and calculating and outputting the value of the Yanxigong Miao; where the value user is given a higher weight.
Still other of the above preferred embodiments provide a neural network system. The neural network includes:
the emotion analysis network obtained by training according to the preferred embodiment is used for analyzing emotion characteristics of the input social media short text;
and a fusion layer for fusing the emotional characteristics for value evaluation; specifically, the fusion may be performed by averaging the emotional tendencies/emotional characteristics, or may be performed by weighted averaging.
Correspondingly, still other of the preferred embodiments described above provide an apparatus for value assessment using social media short text. The device includes:
the input unit is used for acquiring a social media short text of a topic object to be evaluated; namely, short texts of topic objects to be evaluated on a target social media are obtained;
an evaluation unit, configured to implement the value evaluation method according to the above preferred embodiment, and evaluate the value of the topic object; the method comprises the steps of training an obtained emotion analysis network by the method described in the preferred embodiment, analyzing the short text, and outputting emotion tendency/emotion characteristics; and a fusion module for fusing the emotional tendency/emotional characteristic to evaluate the value of the topic object;
and the output unit is used for outputting the evaluation result, namely the value of the topic object to be evaluated obtained by the evaluation.
Correspondingly, still other of the above preferred embodiments provide a device for social media short text sentiment analysis. The device includes:
the input unit is used for acquiring a target short text; short text that needs to be analyzed that relates to a specific topic object on social media;
the analysis unit comprises an emotion analysis network obtained by training in the preferred embodiment and the method; the target short text is analyzed;
and the output unit is used for outputting the analysis result.
Correspondingly, still further ones of the above-described preferred embodiments provide an electronic device. The electronic device includes:
a memory and a processor;
the memory is used for storing executable instructions;
the processor is used for communicating with the memory to execute the stored executable instructions to complete
Any of the above-described methods for sentiment analysis of social media short texts and/or any of the above-described methods for value assessment using social media short texts are preferred.
Correspondingly, still further ones of the above-described preferred embodiments provide an electronic device. The electronic device includes:
a processor;
the processor comprises any one of the value evaluation devices and/or any one of the short text sentiment analysis devices described in the preferred embodiments above.
Correspondingly, still further ones of the preferred embodiments described above provide a computer program product. The computer program product comprises: computer readable code; the computer readable code, when executed on a device, causes a processor in the device to execute instructions for implementing any of the methods for social media short text sentiment analysis and/or any of the methods for value assessment using social media short text as described in the preferred embodiments above.
Correspondingly, still further ones of the preferred embodiments described above provide a computer-readable storage medium. The computer readable storage medium for storing computer readable instructions; the instructions when executed perform the operations of any of the above-described methods for sentiment analysis of social media short texts and/or any of the above-described methods for value assessment using social media short texts.
The above description is only a specific embodiment of the present invention, but the scope of the present invention is not limited thereto.
Claims (10)
1. A method for social short text sentiment analysis, comprising:
acquiring a target short text;
acquiring a source short text and an evaluation label corresponding to the source short text;
training an emotion analysis network by taking the source short text and the evaluation label as a training sample set;
and inputting the target short text into the emotion analysis network obtained by the training, and analyzing the emotion tendency of the target short text.
2. The method for social short text sentiment analysis according to claim 1, further comprising:
preprocessing a text; the text preprocessing is carried out before the target short text and the source text are input, analyzed and trained;
the text preprocessing comprises extracting keywords and word2 vector.
3. A method for value evaluation by utilizing social short texts is characterized by comprising the following steps:
acquiring a social short text of a topic object to be evaluated;
analyzing the social short text by the method of any one of claims 1-2, and outputting emotional tendency/emotional characteristic;
and fusing the emotional tendency/emotional characteristic to evaluate the value of the topic object.
4. A neural network system, comprising:
the emotion analysis network obtained by training of any one of claims 1-2, used for analyzing the emotion characteristics of the input social short text;
and a fusion layer for fusing the emotional features.
5. An apparatus for value assessment using social short text, comprising:
the input unit is used for acquiring the social short text of the topic object to be evaluated;
an evaluation unit for implementing the value evaluation method of claim 3, evaluating a value of the topic object;
an output unit for outputting said value.
6. An apparatus for social short text sentiment analysis, comprising,
the input unit is used for acquiring a target short text;
an analysis unit comprising the emotion analysis network obtained by the training of any one of claims 1 to 2; the target short text is analyzed;
and the output unit is used for outputting the analysis result.
7. An electronic device, comprising,
a memory and a processor;
the memory is used for storing executable instructions;
the processor is used for communicating with the aforementioned memory to execute the stored executable instructions thereof, so as to complete the operations of the method for emotion analysis of the social short text according to any one of claim 1 and/or the method for value evaluation by using the social short text according to claim 2.
8. An electronic device, comprising,
a processor;
the processor comprises the value evaluation device of claim 5 and/or the short text sentiment analysis device of claim 6.
9. A computer program product, comprising,
computer readable code;
the computer readable code, when executed on a device, causes a processor in the device to execute instructions for implementing the method for sentiment analysis of social short text according to any one of claims 1-2 and/or the method for value evaluation using social short text according to claim 2.
10. A computer-readable program medium characterized in that,
for storing computer readable instructions;
the instructions when executed perform the operations of the method for social short text sentiment analysis of any one of claims 1-2 and/or the method for value assessment using social short text of claim 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010554827.2A CN113821628A (en) | 2020-06-17 | 2020-06-17 | Method, apparatus, program, and medium for value evaluation using social media short text |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010554827.2A CN113821628A (en) | 2020-06-17 | 2020-06-17 | Method, apparatus, program, and medium for value evaluation using social media short text |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113821628A true CN113821628A (en) | 2021-12-21 |
Family
ID=78924333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010554827.2A Pending CN113821628A (en) | 2020-06-17 | 2020-06-17 | Method, apparatus, program, and medium for value evaluation using social media short text |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113821628A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391483A (en) * | 2017-07-13 | 2017-11-24 | 武汉大学 | A kind of comment on commodity data sensibility classification method based on convolutional neural networks |
| CN108665339A (en) * | 2018-03-27 | 2018-10-16 | 北京航空航天大学 | A kind of electric business product reliability index and its implementation estimated based on subjective emotion |
| CN110297902A (en) * | 2019-05-22 | 2019-10-01 | 哈尔滨理工大学 | A kind of commodity evaluation analysis method based on multitask deep learning |
-
2020
- 2020-06-17 CN CN202010554827.2A patent/CN113821628A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107391483A (en) * | 2017-07-13 | 2017-11-24 | 武汉大学 | A kind of comment on commodity data sensibility classification method based on convolutional neural networks |
| CN108665339A (en) * | 2018-03-27 | 2018-10-16 | 北京航空航天大学 | A kind of electric business product reliability index and its implementation estimated based on subjective emotion |
| CN110297902A (en) * | 2019-05-22 | 2019-10-01 | 哈尔滨理工大学 | A kind of commodity evaluation analysis method based on multitask deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111143610B (en) | Content recommendation method and device, electronic equipment and storage medium | |
| CN110020437B (en) | Emotion analysis and visualization method combining video and barrage | |
| CN111324769B (en) | Training method of video information processing model, video information processing method and device | |
| CN107870896B (en) | Conversation analysis method and device | |
| CN109460512B (en) | Recommendation information processing method, device, equipment and storage medium | |
| US10977448B2 (en) | Determining personality profiles based on online social speech | |
| CN106339507B (en) | Streaming Media information push method and device | |
| CN111797820B (en) | Video data processing method and device, electronic equipment and storage medium | |
| CN113469298B (en) | Model training method and resource recommendation method | |
| CN110717325A (en) | Text emotion analysis method and device, electronic equipment and storage medium | |
| CN111597446B (en) | Content pushing method and device based on artificial intelligence, server and storage medium | |
| US11120268B2 (en) | Automatically evaluating caption quality of rich media using context learning | |
| CN110035302B (en) | Information recommendation method and device, model training method and device, computing equipment and storage medium | |
| CN110557659A (en) | Video recommendation method and device, server and storage medium | |
| CN112163560B (en) | Video information processing method and device, electronic equipment and storage medium | |
| CN113315988B (en) | Live video recommendation method and device | |
| CN112995690B (en) | Live content category identification method, device, electronic equipment and readable storage medium | |
| CN111931073B (en) | Content pushing method and device, electronic equipment and computer readable medium | |
| CN111695357A (en) | Text labeling method and related product | |
| CN112995719B (en) | Bullet screen text-based problem set acquisition method and device and computer equipment | |
| CN114186074A (en) | Video search word recommendation method and device, electronic equipment and storage medium | |
| CN113821628A (en) | Method, apparatus, program, and medium for value evaluation using social media short text | |
| Martina et al. | A virtual assistant for the movie domain exploiting natural language preference elicitation strategies | |
| CN113821627A (en) | Neural network, method, device and program for predicting IP work index | |
| CN110019942B (en) | Video identification method and system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211221 |
|
| WD01 | Invention patent application deemed withdrawn after publication |