Improving seller–customer communication process using word embeddings

With the progress in technology innovations, business organizations have preferred usage of online trading instead of traditional ways of trading. Online stores let businessmen offer more variety of products without the need of having big warehouses. At the same time, online shopping also saves time of customers and let them enjoy buying-at-home experience. They have the facility of looking at different qualities and prices of the same products offered by different vendors and buy the most suitable one. Online shopping business has especially got lot of attention after emergence of online social media. There are lot of self-made entrepreneurs as well as business giants with their Facebook pages available for online shopping. With this mode of online shopping getting very popular among masses, there are some inherent problems attached with this mode of online shopping. One of the most common problem on online shopping Facebook pages is question-answering on each post. For each product post published on Facebook page, customers ask lots of questions in the form of comments and then Facebook page admin has to reply each question one by one. This can be a very cumbersome job in case that page has a significant number of customers. In case someone is not replied, goodwill of the company is affected which can in turn affect sales. In this paper, we propose several semantic approaches to tackle with this very important problem of online shopping and compare their results. We propose a simple but effective approach for question extraction from comments on a post and we provide a huge data collection for this formulated task. Results show that word embeddings based approach outperform proposed baseline and other semantic approaches.