An emotion analysis method and system of an active learning framework based on committee query

Abstract

The invention provides an emotion analysis method and system of an active learning framework based on committee query. The method comprises: acquiring training corpus, selecting sample data from the training corpus and marking the sample data; forming a training set, constructing an initial model according to the training set, carrying out data classification according to the user emotion representation; selecting an algorithm according to the committee voting; selecting sample data from the unlabeled training corpus, labeling the sample data, supplementing the sample data into the training set, carrying out update iterative learning on the initial model according to the supplemented training set, obtaining an emotion analysis model, carrying out emotion analysis on an input text through the emotion analysis model, and obtaining an emotion analysis result; According to the method, active learning is introduced, in the emotion analysis task, under the condition that training corpora isreduced, the cost of manual marking is reduced, and meanwhile the performance of the model reaches the expectation.

Description

technical field [0001] The invention relates to the field of computer applications, in particular to an emotion analysis method and system based on an active learning framework of committee inquiry. Background technique [0002] Text sentiment analysis is also known as opinion mining. Sentiment analysis can be considered as a multi-classification task. Generally, users' emotions are divided into three categories: positive, neutral, and negative. [0003] With the development of the Internet and the increase of user subjective comment texts with emotional color, we can easily obtain a large amount of comment data, but manual labeling of a large number of training samples is time-consuming and laborious, and the cost is too high. In addition, too many low-quality training samples will reduce the robustness of the classification model and even lead to "over-learning" problems. [0004] Active learning has achieved long-term development in both theory and practical application....

AI Technical Summary

Problems solved by technology

With the continuous iteration of this process, the set of marked training samples will continue to expand, and the classification accuracy from the beginning of the semester will also be continuously improved, and the iteration will be stopped until the required accuracy is reached, thereby reducing the labeling cost. However, at present The active learning algorithm itself is not very perfect, and there are many problems, such as the selection of initial training samples is too random, the algorithm parameter setting is too fixed, and the learning efficiency is not high. Research

Images