CN111651607A - Information positive and negative emotion analysis method and device, computer equipment and storage medium - Google Patents
Information positive and negative emotion analysis method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111651607A CN111651607A CN202010670967.6A CN202010670967A CN111651607A CN 111651607 A CN111651607 A CN 111651607A CN 202010670967 A CN202010670967 A CN 202010670967A CN 111651607 A CN111651607 A CN 111651607A
- Authority
- CN
- China
- Prior art keywords
- information
- positive
- layer
- emotion analysis
- cnn
- 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
- 230000008451 emotion Effects 0.000 title claims abstract description 62
- 238000004458 analytical method Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 47
- 239000013598 vector Substances 0.000 claims abstract description 32
- 239000011159 matrix material Substances 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 7
- 230000015654 memory Effects 0.000 claims description 18
- 238000011176 pooling Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 description 11
- 238000013528 artificial neural network Methods 0.000 description 9
- 230000006403 short-term memory Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000007787 long-term memory Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013519 translation Methods 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
-
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- 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
- 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
Abstract
The invention discloses a method and a device for analyzing positive and negative emotions of information, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a word vector matrix formed by large-scale corpus training, generating a word index, and outputting the word index as the input of a CNN-BilSTM network through an embedding layer; introducing an attention model to the CNN-BilSTM network; carrying out feature classification by utilizing a full connection layer to obtain a target vector of a target sentence; and carrying out emotion analysis on the result of the feature classification of the full connection layer by using a softmax classifier to obtain an emotion analysis result. The scheme can be used for identifying positive and negative emotions in information in batches and accurately, public opinion analysis is realized, public opinion situation is conveniently known, a user can be effectively helped to classify information in multiple dimensions, and the problem that the emotion trend of the information can be judged while main information and local information of the information can be accurately captured without depending on a large number of manual work aiming at information type information of long texts is solved.
Description
Technical Field
The invention relates to the technical field of natural language processing, in particular to a method and a device for analyzing positive and negative emotions of information, computer equipment and a storage medium.
Background
Emotion analysis techniques are currently widely used in internet applications such as online translation, user evaluation analysis, and opinion mining. Particularly for various emerging network social platforms and shopping websites, the emotional tendency of quickly acquiring the user comments can provide great convenience for merchants in aspects of advertisement putting, hot topic pushing and the like. From the current market demand and the development level of the technology, the research and innovation of the emotion analysis technology has great value and space for improvement.
In the prior art, the existing technical scheme for solving the emotion analysis of the information text comprises an emotion analysis technology based on a dictionary and an emotion analysis technology based on a long-term and short-term memory network; however, the prior art also has more or less problems, such as: the rule design of the dictionary scheme of the dictionary-based emotion analysis technology needs a large amount of manual participation, and the emotion analysis technology based on the long-term and short-term memory network cannot accurately acquire main information and local information of the information.
Obviously, a great deal of manpower, material resources and time are needed for calibrating the emotion values through a manual method. Therefore, it is very important to analyze the emotion value automatically by machine learning method.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Based on the reasons, the invention provides a method and a device for analyzing positive and negative emotions of information, computer equipment and a storage medium.
Disclosure of Invention
In order to meet the above requirement, the first objective of the present invention is to provide a method for analyzing positive and negative information emotions.
The second object of the present invention is to provide an apparatus for analyzing positive and negative information emotion.
The third purpose of the invention is to provide a computer device for positive and negative emotion analysis of information.
It is a fourth object of the invention to provide a non-transitory computer readable storage medium having a computer program stored thereon.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, a method for analyzing positive and negative emotions of information is provided, which includes the following steps:
acquiring a word vector matrix formed by large-scale corpus training, generating a word index, and outputting the word index as the input of a CNN-BilSTM network through an embedding layer;
introducing an attention model to the CNN-BilSTM network;
carrying out feature classification by utilizing a full connection layer to obtain a target vector of a target sentence;
and carrying out emotion analysis on the result of the feature classification of the full connection layer by using a softmax classifier to obtain an emotion analysis result.
In one possible embodiment, the method further includes using a dropout technique to prevent overfitting from combining with the target vectors of the BilTM model in the CNN-BilTM network.
In one possible embodiment, the step of outputting the word index as an input of the CNN-BiLSTM network through the embedding layer further includes performing feature extraction by using a convolution operation.
In a possible embodiment, the step of performing feature extraction by using convolution further includes performing feature extraction on the input text sentence by using a set filter, and obtaining a feature matrix by using a convolution layer.
In a possible embodiment, the step of obtaining the feature matrix by the convolutional layer further includes, after the step of obtaining the feature matrix by the convolutional layer, downsampling the sentence local feature matrix obtained after the convolutional layer by using a pooling layer to obtain an optimal solution of local values.
In one possible embodiment, the downsampling the sentence local feature matrix obtained after the convolutional layer by using the pooling layer includes implementing the pooling operation by using a MaxPooling technique.
In a possible implementation manner, the step of obtaining the target vector of the target sentence by performing feature classification using the fully-connected layer further includes obtaining the target vector by setting a target length of the vector.
In another aspect, the present invention provides an apparatus for analyzing positive and negative information emotion, including:
the index input unit is used for acquiring a word vector matrix formed by large-scale corpus training, generating a word index and outputting the word index as the input of a CNN-BilSTM network through the embedding layer;
the model introducing unit is used for introducing the attention model into the CNN-BilSTM network;
the vector acquisition unit is used for carrying out feature classification by utilizing a full connection layer to obtain a target vector of a target sentence;
and the result analysis unit is used for carrying out emotion analysis on the result of the feature classification of the full connection layer by using the softmax classifier to obtain an emotion analysis result.
In a third aspect, the present invention provides a computer apparatus for analyzing positive and negative information emotion, including a memory, a processor, and an information positive and negative emotion analyzing program stored in the memory and executable on the processor, where the information positive and negative emotion analyzing program, when executed by the processor, implements the information positive and negative emotion analyzing method as described in any one of the above.
In a fourth aspect, the present invention further provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method for positive and negative emotion analysis of information as described in any one of the above.
Compared with the prior art, the invention has the beneficial effects that: according to the information positive and negative emotion analysis method, the attention model is introduced to the CNN-BilSTM network, the full connection layer is used for classifying the features, the softmax classifier is used for conducting emotion analysis on the result of feature classification on the full connection layer to obtain the emotion analysis result, positive and negative emotions in the information can be identified in batches and accurately, public opinion analysis is achieved, public opinion situation can be known conveniently, a user can be effectively helped to classify the information in multiple dimensions, and the problem that the emotion trend of the information can be judged while the information is accurately captured by main information and local information of the information without depending on a large number of manual participation is solved.
The invention is further described below with reference to the accompanying drawings and specific embodiments.
Drawings
FIG. 1 is a flowchart illustrating a method for analyzing positive and negative information emotions according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a system for analyzing positive and negative emotions of information in the embodiment of FIG. 1;
FIG. 3 is a block diagram of an embodiment of an apparatus for analyzing positive and negative information emotions according to the present invention;
FIG. 4 is a block diagram of a computer apparatus for negative and positive information emotion analysis according to an embodiment of the present invention;
FIG. 5 is a block diagram of one embodiment of a non-transitory computer readable storage medium according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
As shown in the method flowchart of fig. 1, a method for analyzing positive and negative information feelings according to a first embodiment of the present invention includes the following steps:
step S1, obtaining a word vector matrix formed by large-scale corpus training and generating a word index, and outputting the word index as the input of the CNN-BilSTM network through the embedding layer;
step S2, introducing an attention model to the CNN-BilSTM network;
step S3, performing feature classification by using a full connection layer to obtain a target vector of a target sentence;
and step S4, performing emotion analysis on the result of the feature classification of the full connection layer by using the softmax classifier to obtain an emotion analysis result.
In which a system structure for analyzing positive and negative emotions of information is constructed through steps S1-S4 (as shown in FIG. 2).
In combination with the above system structure, the present invention mainly comprises two parts: firstly, constructing a CNN-BilSTM network, and secondly, introducing an attention model.
The process of analyzing the information by adopting the system structure comprises the following steps:
the local features are extracted through the CNN, the CNN is a feedforward neural network, and the model structure of the CNN mainly comprises an input layer, a convolution layer, a pooling layer, a full-connection layer and an output layer. And taking the output of the embedded layer as input, completing the work of feature extraction through convolution operation, completing the feature extraction of the input text sentence through a set filter, and obtaining a feature matrix after passing through the convolution layer. And in the pooling layer, the sentence local feature matrix C obtained after the convolutional layer is subjected to down-sampling to obtain the optimal solution of the local value. And finally, connecting the full connection layer to obtain a target vector of the target sentence.
In addition, as a basis for implementing the above steps, a Convolutional Neural Network (CNN) is a kind of feed forward neural network (feed forward neural network) including convolution calculation and having a deep structure, and is one of typical algorithms of deep learning (deep learning). Convolutional Neural Networks have a feature learning (rendering) capability, and can perform Shift-Invariant classification (Shift-Invariant classification) on input information according to a hierarchical structure thereof, and are therefore also called "Shift-Invariant Artificial Neural Networks (SIANN)".
Bidirectional long short term memory network (BilSTM): the main structure of the bidirectional long and short term memory network is composed of two unidirectional long and short term memory networks. At each time t, the input is provided to the two opposite long-short term memory networks, and the output is determined by the two unidirectional long-short term memory networks.
Long and short term memory network: the Long Short-Term Memory network (LSTM) is a time-cycle neural network, which is specially designed to solve the Long-Term dependence problem of the general RNN (cyclic neural network), and all RNNs have a chain form of repeated neural network modules. In the standard RNN, this repeated structure block has only a very simple structure, e.g. one tanh layer. Specifically, it has a Memory state unit (Memory Units) throughout, which forgets, memorizes, outputs, and is controlled by a forget gate, a Memory gate, and an output gate calculated by the hidden state at the previous moment and the current input, retains important information, forgets unimportant information, eliminates the problem of gradient-Explosion (grad-ent expansion) or gradient disappearance in the cyclic neural network, and can effectively extract text information of each frame to be processed in order using the BilSTM, and recognize effective information according to the context. This remedies the loss of text sequence extraction and the loss of long-term preceding speech information for the CNN model. The invention introduces an attention mechanism to represent the inconsistency, so that the model can conveniently and accurately capture the emotional expression words of the information.
Based on this, the invention adopts the convolution neural network and the two-way long and short term memory network to merge, and forms the discriminant system shown in figure 2, which is used for analyzing the positive and negative feelings of the information.
In a preferred embodiment, the method further comprises using a dropout technique to prevent overfitting from combining with the target vectors of the BilTM model in the CNN-BilTM network.
As an alternative embodiment, with reference to fig. 1-2, the step of outputting the word index as the input of the CNN-BiLSTM network through the embedding layer in step S1 further includes performing feature extraction by using a convolution operation.
As an optional embodiment, after the step of completing feature extraction by using convolution operation, the step of completing feature extraction on the input text sentence by using a set filter and obtaining a feature matrix by using a convolution layer may be further included, and specific operations may be shown in fig. 2.
As an optional implementation manner, after the step of obtaining the feature matrix through the convolutional layer, the step of obtaining the feature matrix through the convolutional layer further includes down-sampling the sentence local feature matrix obtained after the convolutional layer by using a pooling layer to obtain an optimal solution of a local value.
Specifically, the operation of downsampling the sentence local feature matrix obtained after the convolutional layer by using the pooling layer includes implementing the pooling operation by using a MaxPooling technology.
In a preferred embodiment, the step S3 further includes obtaining a target vector by setting a target length of the vector.
In other embodiments, the step S3 obtains the target vector required by the user through other features of the set vector.
As a second embodiment of the present invention, as shown in FIG. 3, the present invention further provides an apparatus for positive and negative emotion analysis of information, which includes the following units;
the index input unit 100 is used for acquiring a word vector matrix formed by large-scale corpus training, generating a word index, and outputting the word index as the input of a CNN-BilSTM network through an embedding layer;
a model importing unit 200 for importing an attention model to the CNN-BiLSTM network;
a vector obtaining unit 300, configured to perform feature classification by using a full connection layer to obtain a target vector of a target sentence;
and the result analysis unit 400 is used for performing emotion analysis on the result of the feature classification of the full connection layer by using the softmax classifier to obtain an emotion analysis result.
Wherein, the index input unit 100, the model importing unit 200, the vector obtaining unit 300, and the result analyzing unit 400 correspond to the above steps S1, S2, S3, and S4, respectively, and the present apparatus is intended to implement the steps S1 to S4 by using four units, so that the present apparatus has the beneficial effects of the above method.
Specifically, the unit may include, but is not limited to, an operation interface, a prompt interface, and an implementation of operation software.
As a third embodiment of the present invention, as shown in fig. 4, the present invention provides a computer apparatus for analyzing positive and negative information emotion, which includes a memory 500, a processor 600, and an information positive and negative emotion analyzing program stored in the memory 500 and executable on the processor 600, wherein the information positive and negative emotion analyzing program, when executed by the processor 600, implements the information positive and negative emotion analyzing method as described in any one of the above items.
The Memory 500 may be a Read-Only Memory (ROM) or other types of static storage devices that can store static information and instructions, a Random Access Memory (RAM) or other types of dynamic storage devices that can store information and instructions, an Electrically Erasable Programmable Read-Only Memory (EEPROM), a compact disc Read-Only Memory (CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disks, blu-ray disks, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory may be self-contained and coupled to the processor via a communication bus. The memory may also be integral to the processor.
As a fourth embodiment of the present invention, as shown in fig. 5, the present invention provides a non-transitory computer readable storage medium, on which a computer program 700 is stored, which when executed by a processor, implements the method for positive and negative emotion analysis of information as described in any of the above.
The storage medium may be an internal storage unit of the aforementioned server, such as a hard disk or a memory of the server. The storage medium may also be an external storage device of the device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the device. Further, the storage medium may also include both an internal storage unit and an external storage device of the apparatus.
It should be noted that, as can be clearly understood by those skilled in the art, the detailed implementation process of the positive and negative emotion analysis and check apparatus and each unit for the above information may refer to the corresponding description in the foregoing method embodiments, and for convenience and brevity of description, no further description is provided herein.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, more than one unit or component may be combined or may be integrated into another computer device, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the device of the embodiment of the invention can be merged, divided and deleted according to actual needs.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit 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 invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Accordingly, the scope of the present invention should be determined by the appended claims and their equivalents, which are to be construed as broadly as possible, and in order to clearly illustrate this interchangeability of hardware and software, various illustrative components and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention. It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the computer devices and units described above may refer to corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided by the present invention, it should be understood that the disclosed computer apparatus and method may be implemented in other ways. For example, the computer device embodiments described above are merely illustrative. For example, the division of each unit is only one logic function division, and there may be another division manner in actual implementation. For example, more than one unit or component may be combined or may be integrated into another computer device, or some features may be omitted, or not implemented.
The steps in the method of the embodiment of the invention can be sequentially adjusted, combined and deleted according to actual needs. The units in the computer equipment of the embodiment of the invention can be merged, divided and deleted according to actual needs.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit 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 invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a terminal, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for analyzing positive and negative feelings of information is characterized by comprising the following steps:
acquiring a word vector matrix formed by large-scale corpus training, generating a word index, and outputting the word index as the input of a CNN-BilSTM network through an embedding layer;
introducing an attention model to the CNN-BilSTM network;
carrying out feature classification by utilizing a full connection layer to obtain a target vector of a target sentence;
and carrying out emotion analysis on the result of the feature classification of the full connection layer by using a softmax classifier to obtain an emotion analysis result.
2. The method of claim 1, further comprising using a dropout technique to prevent overfitting from combining with the target vectors of the BilSTM model in the CNN-BilSTM network.
3. The method of claim 1, wherein the step of outputting the word index as an input to the CNN-BiLSTM network via the embedding layer further comprises performing feature extraction by convolution.
4. The method as claimed in claim 3, wherein the step of extracting features by convolution further comprises extracting features of the input text sentence by a filter, and obtaining a feature matrix by convolution layer.
5. The method as claimed in claim 4, wherein the step of obtaining the feature matrix by the convolutional layer further comprises down-sampling the sentence local feature matrix obtained after the convolutional layer by using a pooling layer to obtain an optimal solution of the local value.
6. The method as claimed in claim 5, wherein the step of down-sampling the sentence local feature matrix obtained after the convolutional layer by using a pooling layer comprises using Max boosting technique to realize pooling.
7. The method as claimed in claim 1, wherein the step of performing feature classification using the full link layer to obtain the target vector of the target sentence further comprises obtaining the target vector by setting a target length of the vector.
8. An information positive and negative emotion analyzing device is characterized by comprising the following units:
the index input unit is used for acquiring a word vector matrix formed by large-scale corpus training, generating a word index and outputting the word index as the input of a CNN-BilSTM network through the embedding layer;
the model introducing unit is used for introducing the attention model into the CNN-BilSTM network;
the vector acquisition unit is used for carrying out feature classification by utilizing a full connection layer to obtain a target vector of a target sentence;
and the result analysis unit is used for carrying out emotion analysis on the result of the feature classification of the full connection layer by using the softmax classifier to obtain an emotion analysis result.
9. Computer equipment for positive and negative emotion analysis of information, comprising a memory, a processor and a program for positive and negative emotion analysis of information stored in the memory and executable on the processor, wherein the program for positive and negative emotion analysis of information when executed by the processor implements the method for positive and negative emotion analysis of information according to any of claims 1 to 7.
10. A non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for positive and negative sentiment analysis of information according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010670967.6A CN111651607A (en) | 2020-07-13 | 2020-07-13 | Information positive and negative emotion analysis method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010670967.6A CN111651607A (en) | 2020-07-13 | 2020-07-13 | Information positive and negative emotion analysis method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111651607A true CN111651607A (en) | 2020-09-11 |
Family
ID=72350312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010670967.6A Pending CN111651607A (en) | 2020-07-13 | 2020-07-13 | Information positive and negative emotion analysis method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111651607A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114513351A (en) * | 2022-02-08 | 2022-05-17 | 中国人民解放军海军军医大学 | Remote area information encryption transmission method, system and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109299253A (en) * | 2018-09-03 | 2019-02-01 | 华南理工大学 | A kind of social text Emotion identification model construction method of Chinese based on depth integration neural network |
| CN109508377A (en) * | 2018-11-26 | 2019-03-22 | 南京云思创智信息科技有限公司 | Text feature, device, chat robots and storage medium based on Fusion Model |
| US20190197109A1 (en) * | 2017-12-26 | 2019-06-27 | The Allen Institute For Artificial Intelligence | System and methods for performing nlp related tasks using contextualized word representations |
| CN111368086A (en) * | 2020-03-17 | 2020-07-03 | 昆明理工大学 | CNN-BilSTM + attribute model-based sentiment classification method for case-involved news viewpoint sentences |
-
2020
- 2020-07-13 CN CN202010670967.6A patent/CN111651607A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190197109A1 (en) * | 2017-12-26 | 2019-06-27 | The Allen Institute For Artificial Intelligence | System and methods for performing nlp related tasks using contextualized word representations |
| CN109299253A (en) * | 2018-09-03 | 2019-02-01 | 华南理工大学 | A kind of social text Emotion identification model construction method of Chinese based on depth integration neural network |
| CN109508377A (en) * | 2018-11-26 | 2019-03-22 | 南京云思创智信息科技有限公司 | Text feature, device, chat robots and storage medium based on Fusion Model |
| CN111368086A (en) * | 2020-03-17 | 2020-07-03 | 昆明理工大学 | CNN-BilSTM + attribute model-based sentiment classification method for case-involved news viewpoint sentences |
Non-Patent Citations (1)
| Title |
|---|
| 李洋等: ""基于CNN和BiLSTM网络特征融合的文本情感分析"", 《计算机应用》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114513351A (en) * | 2022-02-08 | 2022-05-17 | 中国人民解放军海军军医大学 | Remote area information encryption transmission method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107066446B (en) | Logic rule embedded cyclic neural network text emotion analysis method | |
| CN110083833B (en) | Method for analyzing emotion by jointly embedding Chinese word vector and aspect word vector | |
| CN107247702A (en) | A kind of text emotion analysis and processing method and system | |
| CN110287320A (en) | A kind of deep learning of combination attention mechanism is classified sentiment analysis model more | |
| CN110866398B (en) | Comment text processing method and device, storage medium and computer equipment | |
| CN111914185B (en) | Text emotion analysis method in social network based on graph attention network | |
| CN112214604A (en) | Training method of text classification model, text classification method, device and equipment | |
| CN107688576B (en) | Construction and tendency classification method of CNN-SVM model | |
| WO2020147409A1 (en) | Text classification method and apparatus, computer device, and storage medium | |
| CN113722438B (en) | Sentence vector generation method and device based on sentence vector model and computer equipment | |
| CN109614611B (en) | Emotion analysis method for fusion generation of non-antagonistic network and convolutional neural network | |
| CN112528637A (en) | Text processing model training method and device, computer equipment and storage medium | |
| Sunarya et al. | Comparison of accuracy between convolutional neural networks and Naïve Bayes Classifiers in sentiment analysis on Twitter | |
| CN112287106A (en) | Online comment emotion classification method based on dual-channel hybrid neural network | |
| Aich et al. | Convolutional neural network-based model for web-based text classification. | |
| CN111985243A (en) | Emotion model training method, emotion analysis device and storage medium | |
| CN112287240A (en) | Case microblog evaluation object extraction method and device based on double-embedded multilayer convolutional neural network | |
| CN114241459B (en) | Driver identity verification method and device, computer equipment and storage medium | |
| CN111651607A (en) | Information positive and negative emotion analysis method and device, computer equipment and storage medium | |
| CN112541082A (en) | Text emotion classification method and system | |
| CN111680132A (en) | Noise filtering and automatic classifying method for internet text information | |
| CN116109980A (en) | Action recognition method based on video text matching | |
| CN109726383B (en) | Article semantic vector representation method and system | |
| Meeki et al. | Deep learning for non verbal sentiment analysis: facial emotional expressions | |
| CN112417858A (en) | Entity weight scoring method, system, electronic 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200911 |
|
| RJ01 | Rejection of invention patent application after publication |