On-line interactive comment support degree tendency prediction method based on game theory

Abstract

The invention discloses an on-line interactive comment support degree tendency prediction method based on the game theory. According to the method, firstly, a support degree computing framework is adopted to capture the support degree tendency contained in on-line comments; secondly, support degree computation is combined with the game theory, a utility function for both parties in support degree interaction is defined, three dominant strategy selection rules are combined, and the mixed Nash equilibrium strategy is used as a prediction result of an interactive behavior. By means of the method, the prediction result is accurate; the method is applied to online public opinion monitoring, word-of-mouth marketing and information prediction to help to make the most reasonable decision and improve the work efficiency.

Description

technical field [0001] The invention belongs to the field of information science and relates to a method for predicting the support degree of online interactive comments. Specifically, it is a game theory-based method for predicting the propensity of online interactive comments. Background technique [0002] The rapid development of social networks has made more and more people accustomed to participating in public discussion on Weibo, QQ and forums, and posting online comments to express their views and attitudes. As an important branch of machine learning and computer linguistics, support analysis includes support calculation and support evolution analysis. The task of support calculation is to identify the polarity of the support of the subjective text and judge the polarity strength. Support evolution is to analyze the evolution of the support of complex interactive text over time. The support analysis of online comments plays a fundamental role in supporting many app...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the fact that traditional support calculation cannot solve the problem of predicting the evolution of support for complex interactive texts, the purpose of the present invention is to provide a method for predicting the propensity of online interactive comments based on game theory. The method first adopts an efficient support The degree calculation framework captures the support tendency contained in online comments, and can accurately calculate the support tendency of the entire comment only by relying on a small amount of tagged vocabulary support, and then combines support calculation with game theory to define The utility function of both sides of the support interaction is obtained, combined with three dominant strategy selection rules, the mixed Nash equilibrium strategy is used as the prediction result of the interaction behavior

Images