Extending a corpus for assessing the credibility of software practitioner blog articles using meta-knowledge

Williams, Ashley ORCID: https://orcid.org/0000-0002-6888-0521 and Shardlow, Matthew (2022) Extending a corpus for assessing the credibility of software practitioner blog articles using meta-knowledge. In: EASE 2022: The International Conference on Evaluation and Assessment in Software Engineering, 13 June 2022 - 15 June 2022, Gothenburg, Sweden.

Preview

Accepted Version Download (439kB) | Preview

Abstract

Practitioner written grey literature, such as blog articles, has value in software engineering research. Such articles provide insight into practice that is often not visible to research. However, a high quantity and varying quality are two major challenges in utilising such material. Quality is defined as an aggregate of a document's relevance to the consumer and its credibility. Credibility is often assessed through a series of conceptual criteria that are specific to a particular user group. For researchers, previous work has found argumentation' and >evidence' to be two important criteria. In this paper, we extend a previously developed corpus by annotating at broader granularity. We then investigate whether the original annotations (sentence level) can infer these new annotations (article level). Our preliminary results show that sentence-level annotations infer the overall credibility of an article with an F1 score of 91%. These results indicate that the corpus can help future studies in detecting the credibility of practitioner written grey literature.