Data Mining: Twitter Posts about Marta Bus

The goal of this study is to evaluate people’s opinions on Atlanta’s Marta bus service through their Twitter posts (tweets). I collected the total numbers of positive, negative, and neutral words found within Twitter users’ tweets that mentioned “Marta bus” from November 5th to November 13th 2018. In this study, I used RStudio, Twitter API, and word banks (the study of Opinion Mining, Sentiment Analysis, and Opinion Spam Detection* ).



• On November 7th, there was a service interrupt on Marta bus. The incident was showing up in the negative category.

• It is found that a lot of these tweets were located in Santa Marta, Columbia, after putting the tweets on the map. Therefore, the methodology of filtering tweets only mentioning “Marta bus” is not ideal for this study.

Database Reference:

Minqing Hu and Bing Liu. “Mining and Summarizing Customer Reviews.” Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2004), Aug 22-25, 2004, Seattle, Washington, USA,

Bing Liu, Minqing Hu and Junsheng Cheng. “Opinion Observer: Analyzing and Comparing Opinions on the Web.” Proceedings of the 14th International World Wide Web conference (WWW-2005), May 10-14, 2005, Chiba, Japan.

Tags: R