With continued increase in information in the form of text, reading is becoming more costly. This is caused by the increase in volume as well as increase in information redundancy. There are ways to summarize text data to reduce the amount of redundancy therefore making reading more efficient. This project uses a statistical approach to create subsets of Amazon product reviews to gather information about overall reviews without reading through all of them. Using different models, we will try to optimize the review subsets, get an insight about the review data, and explore potential improvements for the models and the approach.

Recommended Citation: Gokce E., Kline D., Vetter R., Cummings J., (2021). Automated Text Reduction: Comparison of Reduced Reading List Creation Methods. UNCW MS CSIS Proceedings. V. 15 , N. 2 .