Sentiment analysis method oriented to micro-blog short text

Abstract

The invention discloses a sentiment analysis method oriented to a micro-blog short text. The method comprises the following steps: step 1, collecting micro-blog data including keywords so as to store in a database; step 2, pre-processing the micro-blog data; step 3, loading associated dictionaries; step 4, processing sentence division and filtering sentences which do not include user configuration keywords; step 5, processing word division to the sentences including the keywords and labeling parts of speech; step 6, processing dependency sentence structure analysis to the sentences including subjects by a sentence structure analyzing tool; step 7, judging the polarity of each sentence including subject words; and step 8, judging the polarity of a whole micro-blog after judging the polarities of all sentences including the subject words. According to the sentiment analysis method provided by the invention, sentiment analysis is more specific, so that users can know sentiment attitude of concerned aspects from the micro-blog.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a sentiment analysis method for microblog short texts. Background technique [0002] Sentiment analysis, also known as opinion mining, refers to the automatic identification and extraction of tendentious attitudes, opinions, and emotions from text. In recent years, the research on subjective text (opinion) mining has been very active, and its main feature is to analyze the subjective opinions contained in the text and calculate its semantic polarity. Since sentiment classification can solve the messy phenomenon of various comment information on the Internet to a certain extent, it is convenient for users to locate the required information accurately. powerful means. Due to its huge influence, Weibo has become the first choice for more and more users to express their opinions and emotions, such as liking or hating certain celebrities, comments on certain movi...

AI Technical Summary

Problems solved by technology

The advantage of the method is that the algorithm is simple and efficient, and it has achieved a certain accuracy rate in the positive and negative discrimination of Weibo, but there are still the following problems: 1) The result depends too much on the emotional dictionary defined by it, resulting in insufficient coverage 2) For microblogs with multiple themes and multiple emotional words, it is impossible to determine the sentence simply by adding the polarity of the emotional words. What kind of emotion does the blogger express on a specific topic; 3) It is easy to make a misjudgment by only counting negative words with an even number as positive and an odd number as negative, because it is impossible to determine that a negative word is a negative of an emotional word, and many times Bloggers expressed negative emotions towards multiple entities; 4) did not consider degree adverbs and sentence structure information, and misjudged some rhetorical questions, including turning points, etc.; , often users are more concerned about the emotional attitude towards a specific entity in Weibo, rather than the general positive and negative judgment of the whole Weibo

Images