[1] Pryzant, Reid, Young-joo Chung and Dan Jurafsky. “Predicting Sales from the Language of Product Descriptions.” (2017).
[2] Hu, N., Liu, L. & Zhang, J.J. “Do online reviews affect product sales? The role of reviewer characteristics and temporal effects”. Inf Technol Manage (2008) 9: 201. https://doi.org/10.1007/s10799-008-0041-2
Summary:
The first paper posits that textual product descriptions are also important determinants of consumer choice. They mine more than 90,000 product descriptions on the Japanese e-commerce marketplace Rakuten and propose a novel neural network architecture that leverages an adversarial objective to control for confounding factors, and attentional scores over its input to automatically elicit textual features as a domain-specific lexicon. They show that how textual features and word narratives can predict the sales of each product. However, the second paper focuses on online product reviews provided by consumers, such as reviewer quality, reviewer exposure, product coverage, and temporal effects.
Reflection:
I really enjoy the first paper, since it’s based on neural network architecture and I’m a neural-nets person, which means I’d like to try many research topics on neural nets and feel neural nets are like black box but also like legos: researchers can feel free both invent some creative components and build parts together according to the need of your tasks. Plus, product description + neural nets is an interesting direction. One thing I’ve never expected is that they combined feature selection task with prediction task inside the proposed neural nets, which I feel great because people always use neural nets to do a lot of similar things. In the experiment, some of classmates mentioned health products do not have any brand loyalty, which I don’t think is an issue. If you are an experienced patient, you would know brand loyalty always exists in every category… I would suggest another two things for this paper: 1. give more intuition to the design of neural network architecture due to its black-box property; 2. I’m curious about whether and how the technique can be apply to other different languages besides Japanese.
The pair of paper are perfectly related, because most people can empirically feel that two most important factors influencing their purchase are product description and online reviews. Thus the second paper dives into how online reviews are associated with sales. I feel more difficult to read the second paper with five hypothesis and tons of tables, which are pretty old school, but I’m still impressed by its simplicity and practicability. It seems the paper mainly use data from Amazon.com’s Web Service (AWS), thus I’m a little curious about if the dataset can significantly influence the analysis, because I feel different E-commerce websites truly have distinct styles in online review. For example, online review on Chinese website Taobao is more vivid and customer-engaged, e.g., with tons of pictures and customer conversations in the review section. In that case, I guess researchers probably need to reconsider features of online reviews involved in the analysis. Personally, I’m not that sure which recommendation system, i.e., yes/no or 1-star to 5-star scale, because sometimes I feel difficult to decide whether to recommend an item with both merit and demerit, that’s where 5-star scale helps for people who struggle to make choices.
