Chinese interactive text emotion and topic identification method based on multitask learning

Abstract

The present invention discloses a Chinese interactive text emotion and topic identification method based on multitask learning. In a feature extraction stage of a Chinese interactive text, the Chinese interactive text emotion and topic identification method combines an interaction feature of the Chinese interactive text to extract an orientation feature of the interactive text; in the emotion and topic identification stage, the Chinese interactive text emotion and topic identification method adopts a context-based multitask classification model construction method to perform multitask classification model construction on a training sample of the interactive text; and aiming at the problem of poor classification effect caused by missing of orientation feature data of new users or inactive users in an e-Learning system, the Chinese interactive text emotion and topic identification method adopts a method combining random walk and multitask learning to identify emotion and topic categories of the new users or inactive users.

Description

technical field [0001] The invention relates to a method for recognizing emotion and topic of Chinese interactive text, in particular to a method for recognizing emotion and topic of Chinese interactive text based on multi-task learning. Background technique [0002] With the rapid development of Internet technology, E-Learning is quickly accepted by people with its advantages of "resource sharing" and "anytime, anywhere", but it also has its own shortcomings. Separation, lack of emotional communication and feedback, teachers cannot grasp students' learning dynamics in real time, and it is difficult to give comprehensive and comprehensive learning evaluations to students. In the e-Learning system, how to discover learners' emotions, adjust learners' negative emotions, and identify topics that learners are interested in has become a current research hotspot. [0003] At present, there are many methods for emotion and topic recognition of text, but compared with traditional t...

AI Technical Summary

Problems solved by technology

[0004] At present, patents related to the project, such as "A method for online detection of microblog hot events based on sentiment analysis" (CN201310403005.4) have been authorized, which extracts sentiment from online microblog texts through sentiment analysis, and then realizes online real-time detection The purpose of publishing hot events on Weibo, but this patent does not combine the characteristics of e-Learning interactive text, which is relatively simple

Images