Community comment emotion tendency analysis-based mobile phone game ranking list construction method

A technology of emotional tendency and construction method, which is applied in the field of mobile game ranking construction based on the analysis of the emotional tendency of community comments. Achieve the effect of speeding up discrimination, reducing time, and wide application prospects

Inactive Publication Date: 2016-10-12
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, although these comments are categorized with emotional polarity, these labels cannot correctly reflect the real emotional orientation of the comment, thus misleading other players and causing difficulties to a certain extent in constructing a mobile game

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
  • Community comment emotion tendency analysis-based mobile phone game ranking list construction method
  • Community comment emotion tendency analysis-based mobile phone game ranking list construction method
  • Community comment emotion tendency analysis-based mobile phone game ranking list construction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below in conjunction with specific examples.

[0040] Such as Figure 1 to Figure 3 As shown, the mobile game leaderboard construction method based on community comment sentiment analysis described in this embodiment includes the following steps:

[0041] 1) Preprocessing the evaluation text input by the user, including removing repeated comments and a large number of false comments that appear in a short period of time.

[0042] Remove duplicate comments:

[0043] 1.1) First traverse all the game reviews of the mobile game, build a 2-gram language model for all reviews, and then calculate the similarity value J(A,B) of any two reviews A and B. The similarity calculation formula adopts the Jaccard similarity formula :

[0044] 1.2) If the similarity between any two evaluations A and B exceeds the preset similarity threshold, it is judged that comments A and B are duplicate evaluations, and such duplicate evaluation pa...

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

No PUM Login to view more

Abstract

The invention discloses a community comment emotion tendency analysis-based mobile phone game ranking list construction method. The method comprises the following steps of: 1) pre-processing an evaluation text input by a user; 2) carrying out word segmentation and part-of-speech tagging on pre-processed mobile phone game comments; 3) selecting high-frequency emotion words as emotion characteristics so as to generate all characteristic vectors required by machine learning; 4) inputting the characteristic vectors and evaluation polarity labels into an SVM classifier to carry out model training; (5) arbitrarily inputting a segment of evaluation text by the user, and after carrying out operations of word segmentation, part-of-speech tagging and characterization, automatically carrying out evaluation polarity estimation on the evaluation text by a training model of the SVM classifier; and (6) generating an evaluation situation corresponding to each mobile phone game, and constructing a corresponding mobile phone game positive comment ranking list according to the quantities of positive comments and negative comments. The method for researching the comment polarity through emotion tendency analysis can extend to various fields and has wide application prospects.

Description

technical field [0001] The present invention relates to the technical field of sentiment analysis, in particular to a mobile game leaderboard construction method based on community comment sentiment analysis. Background technique [0002] With the continuous popularization of smart phones and the continuous improvement of the mobile Internet, the development of mobile games is also thriving. Mobile games have become a major interest pillar of mobile phone users nowadays, bringing huge benefits and broad development space to major game developers and middlemen. In the face of the rapidly growing mobile game user base, how to recommend games that meet the players’ interests and preferences, attract as many users as possible, and develop them to retain them has become an important issue for research and discussion in current mobile game applications. [0003] It is obvious that each game has a different number of user reviews, whether in mobile game forum communities or major ...

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
no application Login to view more
IPC IPC(8): G06Q30/06G06K9/62
CPCG06Q30/0631G06F18/214
Inventor 董守斌薛梦婷张晶胡金龙董守玲
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products