CN111291187B - Emotion analysis method and device, electronic equipment and storage medium - Google Patents
Emotion analysis method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111291187B CN111291187B CN202010074496.2A CN202010074496A CN111291187B CN 111291187 B CN111291187 B CN 111291187B CN 202010074496 A CN202010074496 A CN 202010074496A CN 111291187 B CN111291187 B CN 111291187B
- Authority
- CN
- China
- Prior art keywords
- analyzed
- word
- vector
- target dimension
- words
- 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
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
-
- 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
Abstract
The application provides an emotion analysis method, an emotion analysis device, electronic equipment and a storage medium, wherein the emotion analysis method comprises the following steps: acquiring a text to be analyzed; dividing the text to be analyzed into a plurality of words to be analyzed including target dimension words; based on each word to be analyzed and the trained semantic extraction model, obtaining semantic feature vectors of each word to be analyzed; determining the attention weight of the target dimension word to each word to be analyzed based on each semantic feature vector, and determining the first vector of the text to be analyzed based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed; and determining emotion analysis results corresponding to the target dimension words based on the first vector of the text to be analyzed and the second vector of the target dimension words. According to the scheme, the attention weight of the target dimension word to each word to be analyzed is utilized to determine the associated information between the target dimension word and the text context, so that emotion analysis can be performed more completely and accurately.
Description
Technical Field
The present invention relates to the field of computer processing technologies, and in particular, to an emotion analysis method, an emotion analysis device, an electronic device, and a storage medium.
Background
With the rapid development of the internet, the number of network users has increased dramatically, and a great deal of valuable comment information such as people, events, products, etc. is generated in the process of information interaction. For example, in the fields of e-commerce, intelligent tourism, network taxi taking and the like, users evaluate the commodity quality, service and other multidimensional degrees after consuming, each dimension contains rich emotion information, and the user behavior can be better understood through mining the emotion information, so that the development direction of an event is predicted.
The main flow of the related emotion analysis is generally that firstly, single user comments are analyzed to give emotion polarities, and then the emotion polarities of all the user comments are aggregated to obtain a final analysis result. Many user reviews do not purely express one polarity of emotion. For example, a user commentary after a meal, "the restaurant atmosphere is good, and the dishes taste well, i.e., the attendant's attitudes are somewhat poor. The user evaluates the comments from three dimensions, namely an environment, a taste and a service, and the overall emotion polarity of the comments is given only, so that larger information loss or analysis deviation can be generated.
Disclosure of Invention
In view of the foregoing, an object of the present application is to provide an emotion analysis method, an emotion analysis device, an electronic device and a storage medium, so as to improve the integrity and accuracy of emotion analysis.
Mainly comprises the following aspects:
in a first aspect, the present application provides a method of emotion analysis, the method comprising:
acquiring a text to be analyzed;
dividing the text to be analyzed into a plurality of words to be analyzed including target dimension words;
based on each word to be analyzed and the trained and trained cyclic neural network semantic extraction model, semantic feature vectors aiming at the target dimension word and semantic feature vectors of other words to be analyzed in the plurality of words to be analyzed except the target dimension word are obtained;
determining the attention weight of the target dimension word to each word to be analyzed based on the semantic feature vector of the target dimension word and the semantic feature vectors of the other words to be analyzed, and determining a first vector corresponding to the text to be analyzed based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed;
And determining emotion analysis results corresponding to the target dimension words based on the first vector of the text to be analyzed and the second vector of the target dimension words.
In one embodiment, the obtaining, based on each word to be analyzed and the trained recurrent neural network semantic extraction model, a semantic feature vector for the target dimension word and semantic feature vectors of other words to be analyzed in the plurality of words to be analyzed except the target dimension word includes:
inputting each word to be analyzed into a trained word vector conversion model to obtain word vectors corresponding to each word to be analyzed;
inputting word vectors corresponding to the words to be analyzed into a trained cyclic neural network semantic extraction model to obtain semantic feature vectors aiming at the target dimension words and semantic feature vectors of other words to be analyzed except the target dimension words in the plurality of words to be analyzed.
In one embodiment, the determining the attention weight of the target dimension word to each word to be analyzed based on the semantic feature vector of the target dimension word and the semantic feature vectors of the other words to be analyzed includes:
Determining a first product based on the semantic feature vector of the word to be analyzed and the semantic feature vector of the target dimension word for each word to be analyzed; and determining a second product based on the semantic feature vector of the word to be analyzed and a second vector of the target dimension word;
determining a ratio between the first product and the product value; the product sum value is determined by semantic feature vectors of the words to be analyzed and semantic feature vectors of the words with the target dimension;
and determining the attention weight of the target dimension word for each word to be analyzed based on the determined ratio and the second product.
In one embodiment, the determining the first vector corresponding to the text to be analyzed based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed includes:
for each word to be analyzed, carrying out product operation on the semantic feature vector of the word to be analyzed and the attention weight of the target dimension word to the word to be analyzed to obtain a third product;
and carrying out summation operation on the third product corresponding to each word to be analyzed to obtain a first vector corresponding to the text to be analyzed.
In one embodiment, the determining, based on the first vector of the text to be analyzed and the second vector of the target dimension word, an emotion analysis result corresponding to the target dimension word includes:
assigning a first weight and a second weight to the first vector and the second vector, respectively;
performing product operation on the first vector and the first weight to obtain a fourth product, and performing product operation on the second vector and the second weight to obtain a fifth product;
and carrying out summation operation on the fourth product and the fifth product to obtain an emotion analysis result corresponding to the target dimension word.
In one embodiment, the method further comprises: training the cyclic neural network semantic extraction model and the attention weight;
the cyclic neural network semantic extraction model and the attention weight are obtained through training based on the obtained analysis text samples and text labeling information corresponding to dimension words in each analysis text sample.
In a second aspect, the present application further provides an emotion analysis device, including:
the acquisition module is used for acquiring the text to be analyzed;
The dividing module is used for dividing the text to be analyzed into a plurality of words to be analyzed including words of target dimension;
the generation module is used for obtaining semantic feature vectors aiming at the target dimension words and semantic feature vectors of other words to be analyzed except the target dimension words in the plurality of words to be analyzed based on each word to be analyzed and the trained circulating neural network semantic extraction model;
the determining module is used for determining the attention weight of the target dimension word to each word to be analyzed based on the semantic feature vector of the target dimension word and the semantic feature vectors of the other words to be analyzed, and determining the first vector corresponding to the text to be analyzed based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed;
and the analysis module is used for determining emotion analysis results corresponding to the target dimension words based on the first vector of the text to be analyzed and the second vector of the target dimension words.
In one embodiment, the apparatus further comprises:
the training module is used for training the cyclic neural network semantic extraction model and the attention weight;
The cyclic neural network semantic extraction model and the attention weight are obtained through training based on the obtained analysis text samples and text labeling information corresponding to dimension words in each analysis text sample.
In a third aspect, the present application further provides an electronic device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor in communication with the memory via the bus when the electronic device is running, the processor executing the machine-readable instructions to implement the steps of the emotion analysis method of any of the first aspect and its various embodiments.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the emotion analysis method of the first aspect and any of its various embodiments.
By adopting the scheme, firstly, the text to be analyzed can be divided into a plurality of words to be analyzed comprising target dimension words, semantic feature vectors aiming at the target dimension words and semantic feature vectors of other words to be analyzed except the target dimension words in the plurality of words to be analyzed can be obtained based on each divided word to be analyzed and a trained cyclic neural network semantic extraction model, then the attention weight of the target dimension words to each word to be analyzed can be determined based on the semantic feature vectors of each word to be analyzed and the attention weight of the target dimension words to the word to be analyzed, the first vector corresponding to the text to be analyzed is determined based on the first vector of the text to be analyzed and the second vector of the target dimension words, and finally the emotion analysis result corresponding to the target dimension words is determined. That is, when emotion analysis is performed on the text to be analyzed, the method and the device utilize the attention weights of the target dimension words to the words to be analyzed to determine the associated information between the target dimension words and the text context, so that emotion analysis can be performed more completely and accurately.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an emotion analysis method according to an embodiment of the present application;
FIG. 2 is a flow chart of another emotion analysis method according to an embodiment of the present application;
FIG. 3 is a flowchart of another emotion analysis method according to an embodiment of the present application;
FIG. 4 is a flowchart of another emotion analysis method according to an embodiment of the present application;
FIG. 5 shows a schematic application of an emotion analysis method according to an embodiment of the present application;
fig. 6 shows a schematic structural diagram of an emotion analysis device according to a second embodiment of the present application;
Fig. 7 shows a schematic structural diagram of an electronic device according to a third embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
Considering emotion analysis in the related technology, firstly, analyzing a single user comment to give emotion polarities, and then, aggregating the emotion polarities of all the user comments to obtain a final analysis result. However, many user comments do not purely express one emotion polarity, and in this case, if only the overall emotion polarity of the comment is given, a larger information loss or analysis deviation will occur. Based on the above, the embodiment of the application provides at least one emotion analysis scheme to improve the integrity and accuracy of emotion analysis.
For the sake of understanding the present embodiment, first, a detailed description will be given of an emotion analysis method applied for by an embodiment of the present application, and an execution subject of the emotion analysis method provided by the embodiment of the present application is generally an electronic device with a certain computing capability, where the electronic device includes, for example: the terminal device, or server or other processing device, may be a User Equipment (UE), mobile device, user terminal, cellular phone, cordless phone, personal digital assistant (Personal Digital Assistant, PDA), handheld device, computing device, vehicle mounted device, wearable device, etc. In some possible implementations, the emotion analysis method may be implemented by way of a processor invoking computer readable instructions stored in a memory.
The emotion analysis method provided in the embodiment of the present application will be described below by taking an execution subject as a server as an example.
Example 1
Referring to fig. 1, a flowchart of an emotion analysis method provided in an embodiment of the present application specifically includes the following steps:
s101, acquiring a text to be analyzed;
s102, dividing a text to be analyzed into a plurality of words to be analyzed including target dimension words;
S103, obtaining semantic feature vectors aiming at target dimension words and semantic feature vectors of other words to be analyzed except the target dimension words in the multiple words to be analyzed based on the words to be analyzed and the trained semantic extraction model;
s104, determining the attention weight of the target dimension word to each word to be analyzed based on the semantic feature vector of the target dimension word and the semantic feature vectors of other words to be analyzed, and determining a first vector corresponding to the text to be analyzed based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed;
s105, determining emotion analysis results corresponding to the target dimension words based on the first vector of the text to be analyzed and the second vector of the target dimension words.
After the semantic extraction model is obtained through training, the embodiment of the application can extract the semantic feature vector based on the semantic extraction model, and the first vector corresponding to the text to be analyzed can be determined based on the extracted semantic feature vector, so that emotion analysis can be performed based on the first vector.
Before extracting semantic feature vectors based on a semantic extraction model, the method can firstly perform word segmentation processing on the text to be analyzed to obtain a plurality of words to be analyzed. In order to facilitate the integrity of emotion analysis, before extracting semantic feature vectors based on a semantic extraction model, the embodiments of the present application need to identify target dimension terms in terms to be analyzed, where the target dimension terms are used to characterize dimension terms in the text to be analyzed that can have emotion analysis intent, for example, quality of service, logistics speed, and the like.
The target dimension words can be one or a plurality of. For example, for a text to be analyzed that "the piece of clothing is very good in quality but very slow in logistics", both quality and logistics can be taken as target dimension words, i.e., words to be analyzed intended to focus on emotion analysis results can be selected as target dimension words.
After determining a plurality of words to be analyzed including the target dimension word, extracting semantic feature vectors of the words to be analyzed including the target dimension word based on the trained semantic extraction model.
When extracting the semantic feature vectors, the method can firstly input each word to be analyzed into a trained word vector conversion model, and then extract the semantic feature vectors based on the trained semantic extraction model.
After each word to be analyzed is obtained, the word to be analyzed, which is a natural language, can be converted into digital information in a vector form based on a mathematical method word2vec so as to facilitate machine recognition, and the process is called encoding (Encoder). That is, a word vector converted by the word vector conversion model is used to represent a word, and then the word vector is used as an input feature of the semantic extraction model.
The word vector conversion models which can be adopted in the embodiment of the application mainly comprise two types, namely a word vector conversion model based on One-time representation (One-hot Representation) and a word vector conversion model based on distributed representation (Distributed Representation).
The former word vector conversion model uses a long vector to represent a word, the vector length is the word size N of a dictionary, each vector has only one dimension of 1, the rest dimensions are all 0, and the position of 1 represents the position of the word in the dictionary. That is, the former word vector conversion model stores word information in a sparse manner, that is, each word is assigned a digital identifier, and the representation is relatively compact. The latter word vector conversion model needs to perform semantic representation according to the context information, that is, the words appearing in the same context have similar semantics. That is, the latter word vector conversion model stores word information in a dense manner, and the representation is relatively complex. Considering that the former word vector conversion model based on One-hot Representation often encounters dimension disasters when solving practical problems and potential relations between vocabularies cannot be revealed, the latter word vector conversion model based on Distributed Representation can be adopted to carry out vector representation on tag information in practical implementation, the dimension disasters are avoided, and associated attributes between vocabularies are mined, so that the accuracy of semantic expression is improved.
In the embodiment of the application, after the word vector is extracted based on the word vector conversion model, the extraction of the semantic feature vector can be performed based on the trained semantic extraction model. Considering the extraction process of semantic feature vectors as a key step of the emotion analysis method provided in the embodiment of the present application, a training process of a semantic extraction model for performing semantic extraction can be described briefly next.
After training the semantic extraction model, acquiring each analysis text sample and text labeling information corresponding to the dimension word in each analysis text sample, wherein in the embodiment of the application, semantic labeling can be performed based on the emotion state of the dimension word, for example, when determining that the emotion state can be divided into positive emotion and negative emotion, positive emotion is labeled as 1, and negative emotion is labeled as 0; for another example, when it is determined that the emotional state can be classified into positive emotion, negative emotion and neutral emotion, it can be labeled as 1, 0 and-1, respectively. The semantic annotation is merely an example, and in a specific application, the semantic annotation may be performed not only based on the coarse classification, but also after the coarse classification emotion is further refined, and the semantic annotation is not specifically limited herein.
After the semantic annotation is performed, the semantic extraction model to be trained and the attention weight based on the acquired analysis text samples and text annotation information corresponding to the dimension words in each analysis text sample can be trained, and training of the semantic extraction model is performed, namely, the process of training parameters of the semantic extraction model.
In a specific application, the semantic extraction model maps an input vector to an output vector. The embodiment of the application can adopt a special type of cyclic neural network (Recurrent Neural Networks, RNN) -Long Short-Term Memory (LSTM) network for model training, wherein the LSTM comprises 3 gate structures for controlling the transmission and change of information, and the three gate structures are respectively as follows: an input door, an output door and a forget door. The input gate is used for controlling the proportion occupied by the input signal, the output gate is used for controlling the proportion occupied by the output signal, and the forgetting gate is used for controlling the proportion of the past information forgotten. The three work cooperatively to control the operation mode inside the LSTM. Each time it receives a signal input and outputs a signal and changes its internal parameter state, which is a model very suitable for processing sequence information features. In this way, the embodiment of the application adopts the LSTM network to gradually master various basic knowledge through repeated iterative learning, and finally learns how to generate a voice feature vector meeting the requirements according to the word vector.
In the emotion analysis method provided by the embodiment of the application, in the process of model training, in order to measure whether the result output by the model is matched with the pre-labeled information, various characterization modes of a loss function can be adopted for implementation. In the embodiment of the application, the cross entropy can be used as a loss function to measure the matching degree of the information, and the cross entropy loss is mainly considered to avoid the problem that training cannot be continued due to the fact that the gradient existing in the smaller error is small, so that the robustness of training is good.
Considering the influence of the target dimension word on the emotion analysis result of the text to be analyzed, the embodiment of the application can determine the attention weight of the target dimension word on each word to be analyzed based on the semantic feature vector of each word to be analyzed, so as to determine the emotion analysis result corresponding to the target dimension word according to the attention weight.
Taking the text to be analyzed, which is "the clothes have very good quality but very slow logistics", as an example, if a two-classification mode is adopted, the emotion analysis result is positive for the target dimension word of quality, and the emotion analysis result is negative for the target dimension word of logistics.
According to the method and the device for determining the emotion analysis results, emotion analysis results corresponding to the target dimension words can be determined based on the splicing results of the first vector of the text to be analyzed and the second vector of the target dimension words. Wherein the second vector of related target dimension terms may be a vector representation of related target dimension terms. Regarding the first vector of the text to be analyzed, the first vector of the text to be analyzed may be determined based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed.
In the embodiment of the application, the attention weight can be determined based on the semantic feature vector of the target dimension word and the semantic feature vector of other words to be analyzed. In view of the critical role of the determination of the attention weight on the first vector corresponding to the text to be analyzed, the above-described process of determining the attention weight may be described herein with reference to fig. 2.
S201, determining a first product according to semantic feature vectors of words to be analyzed and semantic feature vectors of words in target dimensions; and determining a second product based on the semantic feature vector of the word to be analyzed and a second vector of the target dimension word;
s202, determining a ratio between the first product and the product sum value; the product sum value is determined by the semantic feature vector of each word to be analyzed and the semantic feature vector of the target dimension word;
s203, determining the attention weight of the target dimension word for each word to be analyzed based on the determined ratio and the second product.
Here, for each word to be analyzed, first, a first product may be determined based on the semantic feature vector of the word to be analyzed and the semantic feature vector of the target dimension word, and a second product may be determined based on the semantic feature vector of the word to be analyzed and the second vector of the target dimension word, then a ratio between the first product and the product sum may be determined, and finally, the attention weight of the target dimension word for each word to be analyzed may be determined based on the determined ratio and the second product. The product and the value are determined by the semantic feature vector of each word to be analyzed and the semantic feature vector of the target dimension word.
That is, the embodiment of the application can determine the influence of the target dimension word on different words to be analyzed based on the weight calculation strategy, taking the text to be analyzed that the quality of the piece of clothes is very good, but the logistics is very slow as an example, aiming at the word to be analyzed that the quality of the target dimension word is good, the influence of the target dimension word quality is far more than the influence of other words, so that the emotion vocabulary most relevant to the quality of the target dimension word can be determined, and the accuracy of emotion analysis is further improved. Similarly, for words to be analyzed like "slow", the influence of the target dimension word logistics is far beyond the influence of other words, so that emotion words most relevant to the target dimension word logistics can be determined, emotion analysis can be performed on the dimension of quality, emotion analysis can be performed on the dimension of logistics, and the integrity of emotion analysis is further improved.
After determining the attention weight of the target dimension word for each analysis word, a first vector corresponding to the text to be analyzed may be determined. As shown in fig. 3, the above-mentioned first vector determining process specifically includes the following steps:
S301, carrying out product operation on semantic feature vectors of words to be analyzed and attention weights of target dimension words to be analyzed to obtain a third product;
s302, carrying out summation operation on the third product corresponding to each word to be analyzed to obtain a first vector corresponding to the text to be analyzed.
For each word to be analyzed, the semantic feature vector of the word to be analyzed and the target dimension word can be used for carrying out product operation on the attention weight of the word to be analyzed, and the third product corresponding to each word to be analyzed is subjected to summation operation to obtain a first vector corresponding to the text to be analyzed, that is, the current vector representation of the text to be analyzed can be obtained in a weighted summation mode, so that the final semantic representation can be obtained by utilizing the splicing result between the vector representation and the second vector of the target dimension word, and the emotion analysis result corresponding to each target dimension word can be determined by utilizing the semantic representation.
As shown in fig. 4, the process of determining the emotion analysis result by using the final semantic representation according to the embodiment of the present application includes the following steps:
S401, respectively giving a first weight and a second weight to the first vector and the second vector;
s402, performing product operation on the first vector and the first weight to obtain a fourth product, and performing product operation on the second vector and the second weight to obtain a fifth product;
and S403, carrying out summation operation on the fourth product and the fifth product to obtain an emotion analysis result corresponding to the target dimension word.
Here, in the embodiment of the present application, a first weight may be given to a first vector of a text to be analyzed, and a second weight may be given to a second vector of a target dimension word, so that a fourth product may be obtained based on performing a product operation on the first vector and the first weight, a fifth product may be obtained by performing a product operation on the second vector and the second weight, and then a final vector representation may be determined by performing a summation operation on the fourth product and the fifth product, so as to obtain an emotion analysis result corresponding to the target dimension word.
In order to determine the emotion analysis result corresponding to the target dimension word, the final vector representation may be input into a softmax function to obtain a final probability output, for example, for the two classifications, the probability of determining the positive emotion corresponding to the target dimension word, which is the quality, is 98%, and the emotion analysis result is determined to be the positive emotion by setting a probability threshold.
In order to further understand the process of the emotion analysis method provided in the embodiment of the present application, a specific description may be given with reference to fig. 5 and the following formula. Here, the garment quality is still very good, but the logistics is very slow as the text to be analyzed.
(1) The text to be analyzed which is input first can be converted into a word sequence through word segmentation, as shown in fig. 5, "the clothing has very good quality but very slow logistics" can be mapped into a word vector sequence w= { W 1 ,W 2 ,W 3 ,W 4 ,W 5 ,W 6 ,W 7 ,W 8 ,W 9 ,W 10 },W∈R m×n M is the length of the word vectors and n is the length of the input text, and finally these word vectors can be trained with the model as part of the model parameters. Wherein, there are two dimension words, "quality" and "logistics", each training trains the emotion polarity of one dimension word respectively.
(2) Each input word to be analyzed is mapped into a semantic feature vector sequence H= { H through an LSTM network 1 ,H 2 ,H 3 ,H 4 ,H 5 ,H 6 ,H 7 ,H 8 ,H 9 ,H 10 },H∈R m×n M is the length of the hidden vectors and n is the length of the input text, these vectors ultimately being trained with the model as part of the model parameters.
(3) Next H 1 ,H 2 ,H 3 ,H 4 ,H 5 ,H 6 ,H 7 ,H 8 ,H 9 ,H 10 The attention weight alpha can be obtained together with the corresponding target words through an attention mechanism 1 ,α 2 ,α 3 ,α 4 ,α 5 ,α 6 ,α 7 ,α 8 ,α 9 ,α 10 The calculation formula of the attention weight is as follows Wherein W is a ∈R m×n Word vectors representing dimension words in sentences, H.epsilon.R m×n Represents a hidden layer vector output through LSTM, m is a wordThe length of the vector, n is the input text length, H a Representing dimension word W a Hidden layer vector output through LSTM, H i Ith word W representing input text i Hidden layer vector, aεR, output through LSTM 1×1 ,b∈R 1×1 ,Q∈R n×n As parameter, alpha i Represents the attention weight of the ith word, [ H ] T *Q*W a ] i Representation (H) T *Q*W a )∈R m×n The i-th position component of the vector.
(4) After the attention weight of the hidden layer vector is obtained, the hidden layer vector is weighted by the attention weight to obtainObtaining the vector representation form (namely a first vector) of the current text input, and finally combining the vector representation form with the word vector W of the dimension word a (namely, the second vector) is spliced to form the complete semantic representation T of the word through a splicing module, and the splicing mode of the splicing module is T=M 1 ×H total +M 2 ×W a Wherein M is 1 ∈R m×m ,M 2 ∈R m×m As a parameter, m is the length of the word vector.
(5) The final vector representation T of the text to be analyzed is obtained in step 4 and then input into the softmax functionAnd obtaining the probability output of the final model. The model may employ cross entropy as a loss function, the formula:
wherein y is i For characterizing the true identity result, T i For characterizing model input results.
In summary, the emotion analysis method provided by the embodiment of the application can simultaneously utilize dimension word information and dimension words and context semantic information, a network architecture is provided, so that a model can utilize more comprehensive and complete word senses in terms of word information characterization, namely, a attention weight generation mode based on the dimension information is provided, and public opinion monitoring depends on accurate and comprehensive understanding of the word senses, therefore, the related model architecture adopted by the embodiment of the application is beneficial to improving the accuracy of the public opinion monitoring based on the dimension words.
Example two
Based on the same application conception, the second embodiment of the present application provides an emotion analysis device corresponding to an emotion analysis method, and since the principle of solving the problem by the device in the embodiment of the present application is similar to that of the emotion analysis method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repetition is omitted.
As shown in fig. 6, the emotion analysis device provided in the embodiment of the present application includes:
an obtaining module 601, configured to obtain a text to be analyzed;
the dividing module 602 is configured to divide the text to be analyzed into a plurality of words to be analyzed including the target dimension word;
The generating module 603 is configured to obtain, based on each word to be analyzed and the trained semantic extraction model, a semantic feature vector for a target dimension word and semantic feature vectors of other words to be analyzed in the multiple words to be analyzed except the target dimension word;
a determining module 604, configured to determine attention weights of the target dimension terms to the terms to be analyzed based on the semantic feature vectors of the target dimension terms and the semantic feature vectors of other terms to be analyzed, and determine first vectors corresponding to the text to be analyzed based on the semantic feature vector of each term to be analyzed and the attention weight of the target dimension terms to the term to be analyzed;
the analysis module 605 is configured to determine an emotion analysis result corresponding to the target dimension word based on the first vector of the text to be analyzed and the second vector of the target dimension word.
In one embodiment, the determining module 604 is configured to determine the attention weight of the target dimension word for each word to be analyzed according to the following steps:
for each word to be analyzed, determining a first product based on the semantic feature vector of the word to be analyzed and the semantic feature vector of the target dimension word; and determining a second product based on the semantic feature vector of the word to be analyzed and a second vector of the target dimension word;
Determining a ratio between the first product and the product value; the product sum value is determined by the semantic feature vector of each word to be analyzed and the semantic feature vector of the target dimension word;
based on the determined ratio and the second product, an attention weight of the target dimension word for each word to be analyzed is determined.
In one embodiment, the determining module 604 is configured to determine a first vector corresponding to the text to be analyzed according to the following steps:
for each word to be analyzed, carrying out product operation on the semantic feature vector of the word to be analyzed and the attention weight of the target dimension word to the word to be analyzed to obtain a third product;
and carrying out summation operation on the third product corresponding to each word to be analyzed to obtain a first vector corresponding to the text to be analyzed.
In one embodiment, the analysis module 605 is configured to determine the emotion analysis result corresponding to the target dimension word according to the following steps:
assigning a first weight and a second weight to the first vector and the second vector, respectively;
performing product operation on the first vector and the first weight to obtain a fourth product, and performing product operation on the second vector and the second weight to obtain a fifth product;
And carrying out summation operation on the fourth product and the fifth product to obtain emotion analysis results corresponding to the target dimension words.
In one embodiment, the apparatus further comprises:
a training module 606 for training the semantic extraction model and the attention weight;
the semantic extraction model and the attention weight are obtained through training based on the obtained analysis text samples and text labeling information corresponding to dimension words in each analysis text sample.
Example III
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the electronic device includes: the processor 701, the memory 702 and the bus 703, the memory 702 storing execution instructions, the processor 701 and the memory 702 communicating via the bus 703 when the apparatus is running, the processor 701 executing the machine-readable instructions stored in the memory 702 implementing the steps of the emotion analysis method according to the first embodiment.
Embodiments of the present application also provide a computer readable storage medium having stored thereon a computer program which, when executed by the processor 701, performs the steps of the emotion analysis method.
Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, and the like, and when the computer program on the storage medium is run, the emotion analysis method can be executed, so that the problem that larger information loss or analysis deviation is generated at present is solved, and the effect of improving the integrity and accuracy of emotion analysis is achieved.
The computer program product of the emotion analysis method provided in the embodiment of the present application includes a computer readable storage medium storing program code, and instructions included in the program code may be used to execute the method in the foregoing method embodiment, and specific implementation may refer to the method embodiment and will not be described herein.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes or substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. A method of emotion analysis, the method comprising:
acquiring a text to be analyzed;
dividing the text to be analyzed into a plurality of words to be analyzed including target dimension words;
based on each word to be analyzed and the trained semantic extraction model, semantic feature vectors of the target dimension word and semantic feature vectors of other words to be analyzed in the plurality of words to be analyzed except the target dimension word are obtained;
determining the attention weight of the target dimension word to each word to be analyzed based on the semantic feature vector of the target dimension word and the semantic feature vectors of the other words to be analyzed, and determining a first vector corresponding to the text to be analyzed based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed;
Determining emotion analysis results corresponding to the target dimension words based on the first vector of the text to be analyzed and the second vector of the target dimension words;
the determining the attention weight of the target dimension word to each word to be analyzed based on the semantic feature vector of the target dimension word and the semantic feature vectors of the other words to be analyzed comprises the following steps:
determining a first product based on the semantic feature vector of the word to be analyzed and the semantic feature vector of the target dimension word for each word to be analyzed; and determining a second product based on the semantic feature vector of the word to be analyzed and a second vector of the target dimension word;
determining a ratio between the first product and the product value; the product sum value is determined by semantic feature vectors of the words to be analyzed and semantic feature vectors of the words with the target dimension;
determining the attention weight of the target dimension word for each word to be analyzed based on the determined ratio and the second product;
the determining a first vector corresponding to the text to be analyzed based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed includes:
For each word to be analyzed, carrying out product operation on the semantic feature vector of the word to be analyzed and the attention weight of the target dimension word to the word to be analyzed to obtain a third product;
summing the third products corresponding to the words to be analyzed to obtain a first vector corresponding to the text to be analyzed;
the determining, based on the first vector of the text to be analyzed and the second vector of the target dimension word, an emotion analysis result corresponding to the target dimension word includes:
assigning a first weight and a second weight to the first vector and the second vector, respectively;
performing product operation on the first vector and the first weight to obtain a fourth product, and performing product operation on the second vector and the second weight to obtain a fifth product;
and carrying out summation operation on the fourth product and the fifth product to obtain an emotion analysis result corresponding to the target dimension word.
2. The method according to claim 1, wherein the obtaining, based on each word to be analyzed and the trained semantic extraction model, a semantic feature vector for the target dimension word and semantic feature vectors of other words to be analyzed in the plurality of words to be analyzed except the target dimension word includes:
Inputting each word to be analyzed into a trained word vector conversion model to obtain word vectors corresponding to each word to be analyzed;
inputting word vectors corresponding to the words to be analyzed into a trained semantic extraction model to obtain semantic feature vectors aiming at the target dimension words and semantic feature vectors of other words to be analyzed except the target dimension words in the plurality of words to be analyzed.
3. The method according to any one of claims 1-2, wherein the method further comprises: training the semantic extraction model and the attention weight;
the semantic extraction model and the attention weight are obtained through training based on the acquired analysis text samples and text labeling information corresponding to dimension words in each analysis text sample.
4. An emotion analysis device, characterized in that the device comprises:
the acquisition module is used for acquiring the text to be analyzed;
the dividing module is used for dividing the text to be analyzed into a plurality of words to be analyzed including words of target dimension;
the generation module is used for obtaining semantic feature vectors aiming at the target dimension words and semantic feature vectors of other words to be analyzed except the target dimension words in the plurality of words to be analyzed based on the words to be analyzed and the trained semantic extraction model;
The determining module is used for determining the attention weight of the target dimension word to each word to be analyzed based on the semantic feature vector of the target dimension word and the semantic feature vectors of the other words to be analyzed, and determining the first vector corresponding to the text to be analyzed based on the semantic feature vector of each word to be analyzed and the attention weight of the target dimension word to the word to be analyzed;
the analysis module is used for determining emotion analysis results corresponding to the target dimension words based on the first vector of the text to be analyzed and the second vector of the target dimension words;
the determining module is specifically configured to:
determining a first product based on the semantic feature vector of the word to be analyzed and the semantic feature vector of the target dimension word for each word to be analyzed; and determining a second product based on the semantic feature vector of the word to be analyzed and a second vector of the target dimension word;
determining a ratio between the first product and the product value; the product sum value is determined by semantic feature vectors of the words to be analyzed and semantic feature vectors of the words with the target dimension;
Determining the attention weight of the target dimension word for each word to be analyzed based on the determined ratio and the second product;
the determining module is further specifically configured to:
for each word to be analyzed, carrying out product operation on the semantic feature vector of the word to be analyzed and the attention weight of the target dimension word to the word to be analyzed to obtain a third product;
summing the third products corresponding to the words to be analyzed to obtain a first vector corresponding to the text to be analyzed;
the analysis module is specifically configured to:
assigning a first weight and a second weight to the first vector and the second vector, respectively;
performing product operation on the first vector and the first weight to obtain a fourth product, and performing product operation on the second vector and the second weight to obtain a fifth product;
and carrying out summation operation on the fourth product and the fifth product to obtain an emotion analysis result corresponding to the target dimension word.
5. The apparatus of claim 4, wherein the apparatus further comprises:
the training module is used for training the semantic extraction model and the attention weight;
The semantic extraction model and the attention weight are obtained through training based on the acquired analysis text samples and text labeling information corresponding to dimension words in each analysis text sample.
6. An electronic device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor in communication with said memory via the bus when said electronic device is running, said processor executing said machine readable instructions to implement the steps of the emotion analysis method of any of claims 1-3.
7. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the emotion analysis method of any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010074496.2A CN111291187B (en) | 2020-01-22 | 2020-01-22 | Emotion analysis method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010074496.2A CN111291187B (en) | 2020-01-22 | 2020-01-22 | Emotion analysis method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111291187A CN111291187A (en) | 2020-06-16 |
| CN111291187B true CN111291187B (en) | 2023-08-08 |
Family
ID=71030717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010074496.2A Active CN111291187B (en) | 2020-01-22 | 2020-01-22 | Emotion analysis method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111291187B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111930941A (en) * | 2020-07-31 | 2020-11-13 | 腾讯音乐娱乐科技（深圳）有限公司 | Method and device for identifying abuse content and server |
| CN111950258A (en) * | 2020-08-10 | 2020-11-17 | 深圳市慧择时代科技有限公司 | Emotion classification method and device |
| CN112307179A (en) * | 2020-10-21 | 2021-02-02 | 深圳技术大学 | Text matching method, device, equipment and storage medium |
| CN112905790A (en) * | 2021-02-04 | 2021-06-04 | 中国建设银行股份有限公司 | Method, device and system for extracting qualitative indexes of supervision events |
| CN113469197B (en) * | 2021-06-29 | 2024-03-22 | 北京达佳互联信息技术有限公司 | Image-text matching method, device, equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108052505A (en) * | 2017-12-26 | 2018-05-18 | 上海智臻智能网络科技股份有限公司 | Text emotion analysis method and device, storage medium, terminal |
| CN108170681A (en) * | 2018-01-15 | 2018-06-15 | 中南大学 | Text emotion analysis method, system and computer readable storage medium |
| CN108416032A (en) * | 2018-03-12 | 2018-08-17 | 腾讯科技（深圳）有限公司 | A kind of file classification method, device and storage medium |
| CN108959268A (en) * | 2018-07-20 | 2018-12-07 | 科大讯飞股份有限公司 | A kind of text emotion analysis method and device |
| CN109710761A (en) * | 2018-12-21 | 2019-05-03 | 中国标准化研究院 | The sentiment analysis method of two-way LSTM model based on attention enhancing |
| CN109766557A (en) * | 2019-01-18 | 2019-05-17 | 河北工业大学 | A kind of sentiment analysis method, apparatus, storage medium and terminal device |
| CN109918636A (en) * | 2017-12-13 | 2019-06-21 | 上海智臻智能网络科技股份有限公司 | Kansei Information Processing method, computer equipment and computer readable storage medium |
| CN109960793A (en) * | 2017-12-25 | 2019-07-02 | 上海智臻智能网络科技股份有限公司 | Opinion mining device and intelligent terminal |
| CN109960794A (en) * | 2017-12-25 | 2019-07-02 | 上海智臻智能网络科技股份有限公司 | Judge the device and intelligent terminal of text emotion |
| CN110032736A (en) * | 2019-03-22 | 2019-07-19 | 深兰科技（上海）有限公司 | A kind of text analyzing method, apparatus and storage medium |
| CN110222178A (en) * | 2019-05-24 | 2019-09-10 | 新华三大数据技术有限公司 | Text sentiment classification method, device, electronic equipment and readable storage medium storing program for executing |
| CN110377740A (en) * | 2019-07-22 | 2019-10-25 | 腾讯科技（深圳）有限公司 | Feeling polarities analysis method, device, electronic equipment and storage medium |
| CN110427610A (en) * | 2019-06-25 | 2019-11-08 | 平安科技（深圳）有限公司 | Text analyzing method, apparatus, computer installation and computer storage medium |
| CN110704622A (en) * | 2019-09-27 | 2020-01-17 | 北京明略软件系统有限公司 | Text emotion classification method and device and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10902205B2 (en) * | 2017-10-25 | 2021-01-26 | International Business Machines Corporation | Facilitating automatic detection of relationships between sentences in conversations |
-
2020
- 2020-01-22 CN CN202010074496.2A patent/CN111291187B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109918636A (en) * | 2017-12-13 | 2019-06-21 | 上海智臻智能网络科技股份有限公司 | Kansei Information Processing method, computer equipment and computer readable storage medium |
| CN109960794A (en) * | 2017-12-25 | 2019-07-02 | 上海智臻智能网络科技股份有限公司 | Judge the device and intelligent terminal of text emotion |
| CN109960793A (en) * | 2017-12-25 | 2019-07-02 | 上海智臻智能网络科技股份有限公司 | Opinion mining device and intelligent terminal |
| CN108052505A (en) * | 2017-12-26 | 2018-05-18 | 上海智臻智能网络科技股份有限公司 | Text emotion analysis method and device, storage medium, terminal |
| CN108170681A (en) * | 2018-01-15 | 2018-06-15 | 中南大学 | Text emotion analysis method, system and computer readable storage medium |
| CN108416032A (en) * | 2018-03-12 | 2018-08-17 | 腾讯科技（深圳）有限公司 | A kind of file classification method, device and storage medium |
| CN108959268A (en) * | 2018-07-20 | 2018-12-07 | 科大讯飞股份有限公司 | A kind of text emotion analysis method and device |
| CN109710761A (en) * | 2018-12-21 | 2019-05-03 | 中国标准化研究院 | The sentiment analysis method of two-way LSTM model based on attention enhancing |
| CN109766557A (en) * | 2019-01-18 | 2019-05-17 | 河北工业大学 | A kind of sentiment analysis method, apparatus, storage medium and terminal device |
| CN110032736A (en) * | 2019-03-22 | 2019-07-19 | 深兰科技（上海）有限公司 | A kind of text analyzing method, apparatus and storage medium |
| CN110222178A (en) * | 2019-05-24 | 2019-09-10 | 新华三大数据技术有限公司 | Text sentiment classification method, device, electronic equipment and readable storage medium storing program for executing |
| CN110427610A (en) * | 2019-06-25 | 2019-11-08 | 平安科技（深圳）有限公司 | Text analyzing method, apparatus, computer installation and computer storage medium |
| CN110377740A (en) * | 2019-07-22 | 2019-10-25 | 腾讯科技（深圳）有限公司 | Feeling polarities analysis method, device, electronic equipment and storage medium |
| CN110704622A (en) * | 2019-09-27 | 2020-01-17 | 北京明略软件系统有限公司 | Text emotion classification method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 基于注意力机制Bi-LSTM算法的双语文本情感分析;翟社平等;《计算机应用与软件》(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111291187A (en) | 2020-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111291187B (en) | Emotion analysis method and device, electronic equipment and storage medium | |
| CN109376222B (en) | Question-answer matching degree calculation method, question-answer automatic matching method and device | |
| CN108427707B (en) | Man-machine question and answer method, device, computer equipment and storage medium | |
| CN110009430B (en) | Cheating user detection method, electronic device and computer readable storage medium | |
| CN112164391A (en) | Statement processing method and device, electronic equipment and storage medium | |
| CN116795973B (en) | Text processing method and device based on artificial intelligence, electronic equipment and medium | |
| CN111324696B (en) | Entity extraction method, entity extraction model training method, device and equipment | |
| CN113505204B (en) | Recall model training method, search recall device and computer equipment | |
| CN112905795A (en) | Text intention classification method, device and readable medium | |
| CN113094578A (en) | Deep learning-based content recommendation method, device, equipment and storage medium | |
| CN112085091B (en) | Short text matching method, device, equipment and storage medium based on artificial intelligence | |
| CN110532562B (en) | Neural network training method, idiom misuse detection method and device and electronic equipment | |
| CN112380421A (en) | Resume searching method and device, electronic equipment and computer storage medium | |
| CN114330704A (en) | Statement generation model updating method and device, computer equipment and storage medium | |
| CN110852071A (en) | Knowledge point detection method, device, equipment and readable storage medium | |
| CN110569355A (en) | Viewpoint target extraction and target emotion classification combined method and system based on word blocks | |
| CN112597299A (en) | Text entity classification method and device, terminal equipment and storage medium | |
| CN117132923A (en) | Video classification method, device, electronic equipment and storage medium | |
| CN111859955A (en) | Public opinion data analysis model based on deep learning | |
| CN116644148A (en) | Keyword recognition method and device, electronic equipment and storage medium | |
| Arbaatun et al. | Hate Speech Detection on Twitter through Natural Language Processing using LSTM Model | |
| CN115129863A (en) | Intention recognition method, device, equipment, storage medium and computer program product | |
| CN114942981A (en) | Question-answer query method and device, electronic equipment and computer readable storage medium | |
| CN114428838A (en) | Content recall method and device, computer equipment and storage medium | |
| CN113761152A (en) | Question-answer model training method, device, equipment and storage medium |
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 |