Implementation of the Lexicon Based Algorithm in Sentiment Analytics for Instagram Accounts at Asian Cyber University

Universities, as progressive educational institutions, have evolved to use social media platforms as their primary communication tool namely Instagram. But, despite the increasingly important role of these social media platforms, many universities have not systematically analyzed user sentiment or responses to the content they share. This creates a void in their understanding of how their institutions are viewed and received by stakeholders. This research aims to fill this gap by conducting an in-depth sentiment analysis of the University's Instagram account. Sentiment analysis towards the University uses data sourced from Instagram social media accounts totaling 637 comment data and after cleaning it becomes 538 comments. The results of this research were classification using the lexicon based method by utilizing the Vader Sentiment library, so the results obtained were positive sentiment of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{6 1. 3 \%}$</tex> or 330 comments which were classified as positive, 2.0% negative or 11 comments which were classified as negative, and 36 neutral. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{6 \%}$</tex> or <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 9 7}$</tex> comments were classified as neutral with a model accuracy of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 1. 0 8 \%}$</tex>. It can be concluded that public opinion towards University on Instagram is positive and shows that University has a very good reputation.