<![CDATA[The need to analyze a product or policy becomes an important thing to measure the level of success. Twitter is currently one of the popular applications used by the public to give their impressions and opinions, both positive, negative and neutral opinions. Diverse public opinion on Twitter can be used as a reference material to get the level of community satisfaction on a product, service or policy. In this study, a sentiment analysis system was created using the TF-IDF and SentiStrength Algorithm. The steps in the research are, firstly, crawling Twitter data using the Twitter API, second preprocessing, thirdly doing spell correction, fourth Word weighting (TF-IDF) and lastly SentiStrength classification, where the results of the classification of tweets have positive, negative or neutral sentiments. In the test data taken using the keyword "child vaccines" as many as 1000 tweets, the results obtained were 54% positive sentiment, 20% negative sentiment and 26% neutral sentiment. Comparison with the same negative data analysis using a different algorithm, namely Naïve Bayes, results in positive sentiment of 55%, 16% and neutral 29%. Decision Tree got 61% positive results, 14% negative and 25% neutral.]]>
Copyrights © 2022
