Societal Impact of IS
Loading...
Paper Type
Complete
Paper Number
2054
Description
Powered by the Internet, the online review market has grown exponentially, providing a trove of information to customers and business. However, cracks have started to appear around the economic, social and environmental sustainability of online reviews and surrounding processes. The root of these concerns lies in the number of reviews having no informational value. With the aim of improving the sustainability of this market, the present research develops and compares seven machine learning approaches to identify waste in online app reviews. The Random Forest approach shows the best performance with accuracy of 0.94. If such approach were implemented to reduce data waste in 11 app stores, 252,611 kg of CO2, US$ 74,392 and 25,880 person hours could be saved. Having demonstrated its potential for app reviews, the developed approach could be extended to achieve greater savings and improve sustainability across different segments and types of online reviews.
Recommended Citation
Savarimuthu, Bastin Tony Roy; Corbett, Jacqueline; Yasir, Muhammad; and Lakshmi, Vijaya, "Using Machine Learning to Improve the Sustainability of the Online Review Market" (2020). ICIS 2020 Proceedings. 14.
https://aisel.aisnet.org/icis2020/societal_impact/societal_impact/14
Using Machine Learning to Improve the Sustainability of the Online Review Market
Powered by the Internet, the online review market has grown exponentially, providing a trove of information to customers and business. However, cracks have started to appear around the economic, social and environmental sustainability of online reviews and surrounding processes. The root of these concerns lies in the number of reviews having no informational value. With the aim of improving the sustainability of this market, the present research develops and compares seven machine learning approaches to identify waste in online app reviews. The Random Forest approach shows the best performance with accuracy of 0.94. If such approach were implemented to reduce data waste in 11 app stores, 252,611 kg of CO2, US$ 74,392 and 25,880 person hours could be saved. Having demonstrated its potential for app reviews, the developed approach could be extended to achieve greater savings and improve sustainability across different segments and types of online reviews.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
4-Socimpact