Automated extraction of product comparison matrices from informal product descriptions

Abstract

Domain analysts, product managers, or customers aim to capture the important features and differences among a set of related products. A case-by-case reviewing of each product description is a laborious and time-consuming task that fails to deliver a condense view of a family of product.In this article, we investigate the use of automated techniques for synthesizing a product comparison matrix (PCM) from a set of product descriptions written in natural language. We describe a tool-supported process, based on term recognition, information extraction, clustering, and similarities, capable of identifying and organizing features and values in a PCM -despite the informality and absence of structure in the textual descriptions of products.We evaluate our proposal against numerous categories of products mined from BestBuy. Our empirical results show that the synthesized PCMs exhibit numerous quantitative, comparable information that can potentially complement or even refine technical descriptions of products. The user study shows that our automatic approach is capable of extracting a significant portion of correct features and correct values. This approach has been implemented in MatrixMiner a web environment with an interactive support for automatically synthesizing PCMs from informal product descriptions. MatrixMiner also maintains traceability with the original descriptions and the technical specifications for further refinement or maintenance by users.

Automated extraction of domain knowledge in practice

“…Except for requirements specifications, some research is focused on extracting features from other types of textual documents, for example, informal product descriptions [1,8,9,29] or online software reviews [4,28]. They also used different techniques, such as K-means [28], Fuzzy C-Means [4], Association Rule Mining [8], to aid feature extraction.…”

Towards complex product line variability modelling: Mining relationships from non-boolean descriptions

“…PCMs may come from various sources, e.g., websites (as for instance Wikipedia), automatic generation, manually built by designers or developers. The main drawback of using PCMs lies in the fact that they are not formalised: in most cases they need to be cleaned to be in a given format and to be automatically processed easily [59,51]. For instance, Table 3 presents an excerpt of a Wikipedia PCM depicting 5 version control software systems depending on 6 characteristics.…”

“…The fact that each PCM has to be manually cleaned before applying our method and performing the experimentations has limited the number of studied PCMs. However, recent research has been conducted on automated extraction and analysis of PCMs [51,50]. This kind of work could ease the process to obtain cleaned PCMs and allow to make our evaluation on a more significant number of PCMs.…”

Seamless Variability Management with the Virtual Platform

“…Over the last decades, researchers focused on heuristic techniques to recover information from legacy codebases, including feature identification [21], [22], [23], feature location [24], [25], [26], variability mining [27], [28], and clone-detection techniques [29], [30]. Unfortunately, such techniques are usually not accurate enough to be applicable in practice, and also require substantial effort to set them up and provide with manual input (e.g., specific program entry points for feature location techniques [31]).…”