The Text Mining and Classification Analyses of Tumor Based on Twitter

ABSTRACT

The study is combined with the text mining and classification method to analyze the tumor-related tweets on Twitter in order to comprehend the public opinion focus on the social media. The contribution of the study included the following two points. First, the study used the text mining method to explore the content of tumor-related tweets and found the keywords according to their frequencies. Second, the study applied the classification analysis with four different algorithms to explore the relationship and the importance of the keywords. The study also found the random forests model with the best performance in four models and concluded that the Twitter users focused more on surgery issues, psychological issues and the technical issues on the topic of tumor.

KEYWORDS:

• Ada Boost algorithm
• Classification
• Fruit Fly Optimization Algorithm
• Random forests
• Text mining
• Tumor

Acknowledgements

The study was partially supported by Macau University of Science and Technology Faculty Research Grant (FRG-19-015-MSB).

Additional information

Funding

The study was partially supported by Macau University of Science and Technology Faculty Research [grant number FRG-19-015-MSB].

Notes on contributors

Shianghau Wu

Shianghau Wu is currently the associate professor of the School of Business, Macau University of Science and Technology. His research interests include the application of data mining to management and social science research.