In the age of big data, the value of different exogenous data has been evolving significantly over time. The usage of the Internet of Things (IoT), such as social media, news releases, conference call transcripts, weather data, etc. can potentially enable the users to obtain meaningful information in order to assist them in their decision-making. This study examines social media information by utilizing text mining techniques and different machine learning algorithms to identify the relevant tweets to the subject and assess the sentiment expressed in the contents. The objective of this study is to examine user-generated content, identify temporal trends and patterns of street cleanliness, analyze whether these trends and patterns are consistent with NYC cleanliness ratings, and assess the performance of municipal services via sentiment analysis. This study extends the research on accessing social media feeds to gain valuable insight regarding the performance of municipal services. The framework presented in this study can be generalized to many other areas where social media information can be utilized. This study should be of great interest to many parties, including municipalities, regulators, citizens, and auditors.

New York City Street Cleanliness: Apply Text Mining Techniques to Social Media Information.

[Annual Meeting Website](https://aaahq.org/Meetings/2020/Annual-Meeting)

[Benefits for Presenters](https://aaahq.org/Meetings/2020/Annual-Meeting/Presenter-Benefits)

 AAA 2020 Virtual Annual Meeting and Conference on Teaching and Learning

The American Accounting Association is the largest community of accountants in academia. Founded in 1916, we have a rich and reputable history built on leading-edge research and publications. The diversity of our membership creates a fertile environment for collaboration and innovation. Collectively, we shape the future of accounting through teaching, research and a powerful network, ensuring our position as thought leaders in accounting.