Journal
2021 ASIA-PACIFIC CONFERENCE ON COMMUNICATIONS TECHNOLOGY AND COMPUTER SCIENCE (ACCTCS 2021)
Volume -, Issue -, Pages 271-276Publisher
IEEE COMPUTER SOC
DOI: 10.1109/ACCTCS52002.2021.00061
Keywords
natural language processing; machine learning; TF-IDF model; news text classification
Ask authors/readers for more resources
This study uses real open-source data to test the accuracy of multiple AI algorithm models and form a composite model named WNTC, which significantly outperforms the traditional model in news text classification tasks.
News text classification plays an important part in the field of news recommendation and intelligent office. Based on the above problem, we use the real open-source data Sogou CS as the research object of this paper to carry out related work, test the accuracy of multiple AI algorithm models, use models with good prediction results, and calculate weights based on the accuracy of each model to form a composite model, named WNTC model. Experimental results on the above real dataset show that our WNTC model significantly outperforms the traditional model, in detail, the accuracy, recall rate, F1-score of the model is 94.27%, 96.02%, 95.14%, which is improved to be compared to the prediction effect of a single AI algorithm model.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available