Procedia Computer Science
Ecommerce websites are filled with international sellers. Product descriptions on these sites are often written in English by non-native speakers. Linguistic imperfections in these descriptions confuse consumers, which may further attenuate their purchase intentions. How descriptive quality/efficacy can be defined and then improved shall be of great interest to all sellers and their consumers. In this research, we attempt to evaluate online product description quality using lexical measurements from linguistics studies. Linguistics measurements of writing quality were mostly developed in pure academic settings. We test and analyze these measurements' applicability in defining and contrasting business description quality using Amazon.com data. Modern classification techniques in the artificial intelligence and machine learning field are deployed in identifying measurement applicability and assessing computational efficiency. Our findings enable automatic identification of descriptive efficacy through artificial intelligence methods on real ecommerce text data.
Data mining, Lexical measurement, Listing description, Online listing, Text mining
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Marketing and Business Analytics; Global Innovation and Leadership
Yang Sun, Shaonan Tian, and Ming Zhou. "Lost in Translation: What Linguistic Measurements Best Measure Text Quality of Online Listings" Procedia Computer Science (2021): 1474-1477. https://doi.org/10.1016/j.procs.2022.01.187