Sentiment Analysis to Assess the Community’s Enthusiasm Towards the Development Chatbot Using an Appraisal Theory
Prima Widyaningrum, Yova Ruldeviyani, Ramanti Dharayani · Procedia Computer Science · 2019
PT Kreatif Dinamika Integrasi will develop a chatbot as the computer program designed to simulate intellectual conversation via text and voice by using Artificial Intelligence (AI). However, because development costs are high enough, it is necessary to gather opinions on the community’s enthusiasm that will support the decision whether the development should or should not to have proceeded. Community sentiment analysis of data obtained from social media Twitter. Appraisal Theory method is exercised utilizing the R Studio tool to perform tweet crawling, preprocessing, scoring and term weighting. R is an open-source language and environment used for statistical computing and graphics. The results of the analysis indicate positive sentiment where the positive and negative comparison ratio was 4,78. The expression of sentiment analysis results by using the NRC library is 547 for “anticipation” sentiment and 728 for “trust” expression so that the technology of chatbot can be developed by the company. Although the results of the analysis of obtained are positive assessment, there is still the negative sentiment in the community, so it is necessary to act to reduce the risk.