Twitter Sentiment Analysis of Covid-19 Using Term Weighting TF-IDF And Logistic Regresion
Imamah Imamah, Fika Hastarita Rachman
Abstract
Covid-19 attack world population, and has brought much impact in all aspects of life. Stay at home and doing less in terms of social interactions. This can have a negative effect on mental health, so in this study we use sentiment analysis to know about mental health through public opinion on Twitter. Dataset which used in this study in this study is covid-19 tweets collected at 30 April 2020. Essentially, this dataset consists of 355384 tweets reviews. Covid-19 tweets will classify with the Logistic Regression method. Based on this research, the accuracy of the covid-19 tweeets sentiment classification is 94.71%.
Topics & Concepts
Sentiment analysisCoronavirus disease 2019 (COVID-19)WeightingLogistic regressionTerm (time)Social mediaComputer sciencetf–idfPopulationArtificial intelligenceMachine learningMedicineWorld Wide WebEnvironmental healthPathologyRadiologyPhysicsQuantum mechanicsInfectious disease (medical specialty)DiseaseSentiment Analysis and Opinion MiningMental Health via WritingAdvanced Text Analysis Techniques