Support vector machine based text sentiment analysis method and device
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of support vector machine and sentiment analysis, applied in the field of information processing, can solve the problem of inaccurate text sentiment classification
Inactive Publication Date: 2016-06-01
CHINA MOBILE COMM GRP CO LTD
View PDF3 Cites 2 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0006] The embodiment of the present invention provides a text sentiment analysis method and equipment based on SVM to solve the problem of inaccurate text sentiment classification existing in the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0022] Embodiment 1 of the present invention provides a text sentiment analysis method based on SVM, such as figure 1 As shown, it is a schematic flow chart of the text sentiment analysis method described in Embodiment 1 of the present invention, and the method may include the following steps:
[0023] Step 101: extract each feature item in the text to be analyzed.
[0024] Wherein, the feature items generally refer to words or vocabulary with corresponding emotional tendencies in the text, such as "beautiful", "elegant" and so on.
[0025] Step 102: Calculate the feature weights of the extracted feature items, and construct a text vector corresponding to the text to be analyzed according to the extracted feature items and the feature weights of each feature item.
[0026] Step 103: Calculate the inter-class distance of each set text class, and according to the calculated inter-class distance of each set text class, select a text class with the largest inter-class distance as...
Embodiment 2
[0074] Embodiment 2 of the present invention provides an SVM-based text sentiment analysis device that can be used to implement the method described in Embodiment 1 of the present invention. Its structural diagram is as follows figure 2 shown, including:
[0075] The extraction module 21 can be used to extract each feature item in the text to be analyzed;
[0076] The construction module 22 can be used to calculate the feature weights of the extracted feature items, and construct a text vector corresponding to the text to be analyzed according to the extracted feature items and the feature weights of each feature item;
[0077] The classification module 23 can be used to calculate the inter-class distance of each set text class, and according to the calculated inter-class distance of each set text class, select a text class with the largest corresponding inter-class distance as the first-level classification, and The rest of the other text categories are used as the second-l...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention discloses a support vector machine (SVM) based text sentiment analysis method and device. The method comprises the steps of extracting feature items in a to-be-analyzed text and constructing a text vector corresponding to the to-be-analyzed text according to the extracted feature items and the calculated feature weights of the feature items; and according to the calculated between-class distance of set text classes, selecting a text class with the corresponding maximum between-class distance as first-stage classification, taking the rest of other text classes as second-stage classification, and classifying the feature items in the text vector by adopting an SVM according to a classification mode that a classification sequence of the first-stage classification is prior to that of the second-stage classification. That is to say, according to the scheme, the classification sequence of the text classes is optimized, for example, the text class with the corresponding maximum between-class distance, namely, the text class easiest to distinguish, is taken as the first-stage classification, so that the accuracy of SVM based text sentiment classification is improved.
Description
technical field [0001] The present invention relates to the technical field of information processing, in particular to a text sentiment analysis method and equipment based on SVM (Support Vector Machine, Support Vector Machine). Background technique [0002] With the emergence and popularization of network information models for users to create content and share content, and the content and forms of network media are becoming more and more abundant, there are more and more texts with personal emotions on the network, especially in various forums, Internet media in the form of Weibo are typical. The contents of these texts are usually users' personal comments on topics such as news and current affairs, regulations and policies, public figures, consumer products, film and television entertainment, etc., which reflect the views and opinions of individual users. Analysis of the content of the text can help users discover product shortcomings in a timely manner, so as to provid...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more