Visualisasi Data Tweet di Sektor Pendidikan Tinggi Pada Saat Masa Pandemi

Abstract

The Covid-19 pandemic has had an impact on many sectors, including higher education. Various public opinions about higher education have emerged on social media during the pandemic, with varying foci of discussion. The purpose of this study is twofold. The first is to compare the results of semantic data analysis with and without stemming. Second, to determine the topic of discussion among Twitter users about higher education. This study was carried out by collecting tweet data for a year during the pandemic, from March 2020 to March 2021. The data then pre-processed using a combination of methods to ensure that there was minimal noise data. The analysis is performed using information theory, bigram phrases, semantic relationship analysis between words, and visualized using gephi in the final stage. The findings of this study explain in detail why the stemming method cannot be used directly for preprocessing data that requires semantic understanding. Data visualization also reveals that Twitter users who talk about higher education are more concerned with campus life and new student admissions. This research evaluates the stemming process because the results show that using stemming eliminates semantic meaning between words. This research also visualizes semantic relationships in tweets about higher education