Lexicon-Based Features on Naive Bayes Modification for Classification of Chinese Film

• Published in: 2022 International Seminar on Application for Technology of Information and Communication (iSemantic) pp. 61 - 65
• Main Authors: Sunarti, S, Wahyono, Irawan Dwi, Putranto, Hari, Saryono, Djoko, Bukhori, Herri Akhmad, Widyatmoko, Tiksno, Rosli, Mohd Shafie, Shukor, Nurbiha A., Abdul Halim, Noor Dayana
• Format: Conference Proceeding
• Language: English
• Published: IEEE 17.09.2022
• Subjects: Chinese Language; Dictionaries; Lexicon Feature; Mood; Motion pictures; Naive Bayes; Seminars; Sentiment analysis; Taxonomy; Video on demand
• ISBN: 9781665488372; 1665488379
• DOI: 10.1109/iSemantic55962.2022.9920399

There are many Chinese movies on the internet for learning Chinese, one of which is on YouTube. This educational film provides negative and positive comments. To get a good movie to learn Chinese, we need to classify positive and negative comments ratings for Chinese learning that teachers can use in this video. In addition, a review of comments is an evolution of Chinese film ratings. The evaluation of comments included includes storytelling, content, model, visual effects, and more. The review has criticisms and comments that include feelings about the movie on Chinese language learning. Commentator helps movie students compare a movie's mood with positive or negative emotion groups. This research uses the naive Bayes taxonomy with the Lexicon Based function in sentiment analysis of comments. The classification process considers the appearance of words of emotional content in the score and the possible score values for positive or negative emotional classes. Based on test results, feature selection accuracy, precision, and recall in the form of stop word exclusion receive scores of 0.91, 0.87, and 0.98, respectively.