Permodelan Topik pada Layanan Akademik Perguruan Tinggi dengan Menggunakan N-Gram

Automation of generating information in academic services are expected to provide convenience in providing academic services to students. Relevant topics can be extracted from social media by calculating the frequency of words asked by social media users. The research focuses on generating question topics on academic services at universities. Topic extraction are obtained through data taken from Instagram social media, so that relevant topics are obtained to get information that is most frequently asked by the public. The N-Gram and Term Frequency are approach to extract the topic. The initial stages in this study include conducting Web Scraping taken from Instagram social media. In this study, text preprocessing was carried out in several stages, namely cleansing, casefolding, stopwords removal and tokenizing, and stemming. The N-Gram approach is carried out by comparing three types, namely unigrams, bigrams and trigrams. The results obtained in this study prove that the bigram produces relevant word pairs in determining academic service topics on social media. This approach produces word pairs that are relevant to academic service topics including graduation list, paying UKT, independent admission, SPANPTKIN and independent test.