The title of a product offering is the consolidation of a product's characteristics in textual format for user consumption. The low quality of the textual content of a product's title can negatively influence the entire shopping experience. The negative experience can start with the impossibility of discovering a desired product, going from problems in identifying a product and its characteristics up to the purchase of an unwanted item. A solution to this problem is to establish an indicator that automatically describes the quality of the product title. With this assessment, it is possible to notify sellers who have registered products with poor quality titles and encourage revisions or suggest improvements. The focus of this work is to show how it is possible to assign a score that indicates the descriptive quality of product offers in an e-commerce marketplace environment using unsupervised methods.

Online social media has become an essential part of our life. This media is often characterized by its diverse content, which is produced by ordinary users. The potential to easily express ideas and opinions has made social media a source of valuable information on a variety of topics. In particular, information containing comments about consumer products has become prevalent. Here, we are interested in linking products mentioned in unstructured user-generated content, namely open discussion forums, to their respective entities in consumer product catalogs. Among the issues associated with this task, ambiguity is a particularly hard problem, as users typically refer to the same product using many different forms and different products may share the same form. We argue that this problem can be effectively solved using a set of evidences that can be easily extracted from social media content and product descriptions. To achieve this, we show which features should be used, how they can be extracted, and then how to combine them through machine learning techniques. Experiments in three different product categories and two different datasets demonstrate that all the sources of evidence here proposed are important, while contextual information is fundamental to achieve higher levels of precision. In fact, our method, although straightforward, was able to achieve an average improvement of 0.17 in precision and 0.13 in F1, when compared to the current state-of-the-art solution.