“Predicting Sales from the Language of Product Descriptions”
by Reid Pryzant, Young-joo Chung, and Dan Jurafsky
“Do Online Reviews Affect Product Sales? The Role of Reviewer Characteristics and Temporal Effects”
by Nan Hu, Ling Liu, and Jie Jennifer Zhang
Both papers here are focused on how corporations are increasingly using social science to better connect with customers and conduct business. This trend has been gaining a large amount of traction recently, but is now undergoing controversy since the privacy questions aimed at Facebook and Cambridge Analytica. These topics should be scrutinized closely in order to verify positive societal growth while avoiding manipulation and malfeasance against the public.
Pryzant et al are trying to estimate buying behavior based off of the textual features present in product descriptions. But was there any preliminary analysis to determine if this complex and novel RNN+GF model was necessary? Could a simpler model be just as effective and have less computational cost? It would still have novelty just by approaching the textual analysis of product descriptions rather than the basic summary statistics that were in the previous studies.
Pryzant’s research focuses on just chocolate and health categories. In particular, ‘health’ must have been an incredibly broad range of products, from fitness tools, weight loss foods, vitamins, books, and medicine. I feel that sticking to just these two categories would bias the results of both categories researched towards phrases such as ‘healthy’ or ‘low-fat’.
I don’t see much information on what Pryzant et al did to verify their training data. Some items listed may have been severely misrepresented in the description. I also believe that the presence of pictures on product sites are a large impact on buying behavior. They immediately convey much information that may not be covered in the descriptions. There is surely a reason so many company marketing agendas focus on graphics and visuals
Does Pryzant’s research translate well to other cultures? Politeness in Japanese culture is fairly well known as a very prominent characteristics of the majority of people there’. The research here gives Politeness status as an influential word group that increases buying behavior in this Japanese market. Could the same work be applied to the USA or other cultures that may not place the same importance socially on politeness?
I am glad Hu et al preferred the simple yes/no recommendation review system. The popular 5-star review system is more subjective and can be unhelpful. In a 5-star review system, a 4-star review is sometimes considered harmful to a product or service. This is partially due to the subjectivity of those who are doing the rating, who can become biased or manipulated quite easily. So a review system that is built to give a finer degree of resolution on their reviews, can actually lead to more bias and noise in the dataset. Perhaps it would be best that most review systems adopt a simple recommend / do not recommend system of review, as there is almost no question as to where the author stands in this straightforward setup.
I am not sure about the Hu’s conclusion that the impact online reviews on sales diminish over time. Another explanation would be that interest in a product naturally decays over time, and leads to lower sales. It would be difficult to effectively measure this effect and also compare it how the impact of online reviews also decline over time.
