Method and device for sentiment analysis of movie reviews
A sentiment analysis, movie technology, applied in the field of review analysis methods and devices, can solve the problem of low accuracy of movie reviews
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0055] A method for sentiment analysis of movie reviews, including the following steps:
[0056] Step 1. Build a dictionary:
[0057] Build a basic sentiment dictionary:
[0058] Summarize the HowNet dictionary and the "Emotional Vocabulary Ontology" dictionary and remove duplicate entries;
[0059] The process of summarizing and removing duplicate entries is as follows:
[0060] Summarize and remove the positive words in HowNet and the repeated entries of the words marked with a polarity of 1 in the "Emotional Vocabulary Ontology" to form commendatory words in the basic emotional dictionary; sum up and remove the negative words in HowNet and the "Emotional Vocabulary Ontology" Marking the repeated entries of the words whose polarity is 2 constitutes the derogatory terms of the basic sentiment dictionary;
[0061] Manually screen the basic sentiment lexicon of the present invention's construction, and do not consider neutral words in the dictionary of the present invention'...
specific Embodiment approach 2
[0154] The process of adopting the SO-PMI algorithm to calculate each word in word1 as described in step 6 of the present embodiment is as follows:
[0155] For the i1th word in word1, use the following formula to calculate the SO-PMI value,
[0156]
[0157] word1 in the formula i1 is the word in the set word1, pword j1 is the word in the set pword, nword j2 is the words in the set nword; count(word1 i1 , pword j1 ) represents the word word1 for the current calculation i with a word pword in pword j1 The number of times it appears in a sentence at the same time, count(word1 i1 ,nword j2 ) for the currently calculated word word1 i1 with a word nword in nword j2 The number of times they appear together in a sentence; In a fixed corpus, a is a constant, preferably n1=n2; q represents a variable.
[0158] Other steps and parameters are the same as those in the first embodiment.
specific Embodiment approach 3
[0160] A movie review sentiment analysis device, the device is used to implement the movie review sentiment analysis method described in the first or second specific embodiment.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com