Analisis Sentimen Komentar Perplexity AI di X Tentang Pendidikan Menggunakan Support Vector Machine

Abstract

Chatbots with Artificial Intelligence are increasingly popular in everyday life. Due to its ability to reason and convey information expressively, Artificial Intelligence (AI) using Natural Language Processing (NLP) models can communicate like humans. Users find one of Perplexity's AI chatbots interesting because it can pinpoint sources of information. As time goes by and the number of Perplexity users increases, sentiment analysis is used to measure user happiness. This sentiment analysis serves as the data source for this research, helping understand how users react to social media X (Twitter). The Support Vector Machines (SVM) method was used in this study, where SVM maximises the distance (margin) between data groups to determine the ideal hyperplane. According to the survey, 90.11% of respondents expressed positive sentiments, 5.30% expressed negative opinions, and 4.69% expressed neutral sentiments. Using a ratio of 80% training data and 20% test data, the f1 score reached 96%, with accuracy and precision of 92% each.