您的位置:首页  > 论文页面

基于MLP模型的影评情感分析研究

发表时间:2021-06-19  浏览量:861  下载量:142
全部作者: 王冬,甘恒,黄文峰,黄政龙,陈中举
作者单位: 长江大学计算机科学学院
摘 要: 为了对IMDb网络电影数据库内的影评文字进行情感分析并保证较高的准确率,提出了基于MLP模型的情感分析算法。通过使用Keras内置的Tokenizer模块建立字典,利用字典将影评文字进行预处理后,通过Keras框架构建MLP模型并训练,对训练后模型的准确率进行评估,最后对测试集的影评进行情感分析。测试结果显示训练后的模型对影评情感分析具有较高的准确率。
关 键 词: 人工智能;情感分析;多层感知机;IMDb
Title: Research on emotion analysis of film review based on MLP model
Author: WANG Dong, GAN Heng, HUANG Wenfeng, HUANG Zhenglong, CHEN Zhongju
Organization: School of Computer Science, Yangtze University
Abstract: In order to analyze the emotion of film review in IMDb and ensure high accuracy, an emotion analysis algorithm based on multilayer perceptron (MLP) model is proposed. The built-in Tokenizer module of Keras is used to build a dictionary, and the film review text is preprocessed by the use of the dictionary. MLP model is build through the Keras framework and trained, and the accuracy of the trained model is evaluated, finally the emotion analysis of film review in the test set is performed. The test results show that the trained model has a high accuracy in the emotion analysis of film review.
Key words: artificial intelligence; emotion analysis; multilayer perceptron; IMDb
发表期数: 2021年6月第2期
引用格式: 王冬,甘恒,黄文峰,等. 基于MLP模型的影评情感分析研究[J]. 中国科技论文在线精品论文,2021,14(2):208-211.
 
3 评论数 0
暂无评论
友情链接