Scholarlink

The wide application of pop-ups in various video platforms has made the study of their sentiment analysis gradually become a hot topic. This study compares the performance of three machine learning methods, namely Support Vector Machine (SVM), Decision Tree (DT), and Naive Bayes (NB), in pop-up sentiment analysis. The captured and preprocessed pop-up data are used to extract features using methods like TF—IDF, and then the above three models are trained separately. The experimental results show that the DT model is better than SVM and NB in pop-up sentiment classification, with an accuracy of 93.5%. The SVM model has a unique advantage in recognizing neutral sentiment, and the SVM model performs better when there is a large proportion of sexual sentiment samples in the dataset. The NB model has a certain balance between negative and neutral sentiment recognition, although the overall performance is worse than that of the decision trees. Future research can be devoted to integrating deep learning models with traditional machine learning methods to improve the accuracy of pop-up sentiment analysis and enhance its application value.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine Learning Model Construction and Multi-dimensional Evaluation for Pop-Up Text Sentiment Analysis

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jingxin Wang,
  • Ling Zhang,
  • Pengquan Shang,
  • Xuanye Chen,
  • Junhua Wu,
  • Yilei Wang

摘要

The wide application of pop-ups in various video platforms has made the study of their sentiment analysis gradually become a hot topic. This study compares the performance of three machine learning methods, namely Support Vector Machine (SVM), Decision Tree (DT), and Naive Bayes (NB), in pop-up sentiment analysis. The captured and preprocessed pop-up data are used to extract features using methods like TF—IDF, and then the above three models are trained separately. The experimental results show that the DT model is better than SVM and NB in pop-up sentiment classification, with an accuracy of 93.5%. The SVM model has a unique advantage in recognizing neutral sentiment, and the SVM model performs better when there is a large proportion of sexual sentiment samples in the dataset. The NB model has a certain balance between negative and neutral sentiment recognition, although the overall performance is worse than that of the decision trees. Future research can be devoted to integrating deep learning models with traditional machine learning methods to improve the accuracy of pop-up sentiment analysis and enhance its application value.