Arkaitz Zubiaga

TL;DR: In this article, the authors introduce a publicly available annotated dataset for abusive language detection in short texts, which includes comments from YouTube, along with contextual information: replies, video, video title, and the original description.

TL;DR: In this article, the authors take the analysis of microblogs back to first principles and lay out what microblog analysis should look like as a foundational programme of work, and describe how this is of fundamental relevance to Human-Computer Interaction's interest in grasping the constitution of people's interactions with technology within the social order.

TL;DR: In this article, a fuzzy term weighting approach is proposed to make the most of the HTML structure for document clustering, which is based on the hypothesis that a good representation can take advantage of how humans skim through documents to extract the most representative words.

TL;DR: This work presents a study on whether unlabeled data could improve results for multiclass web page classification tasks using Support Vector Machines and encourages to rely only on labeled data, both for improving performance and for reducing the computational cost.

TL;DR: In this paper, the authors provide an overview of research in data mining and natural language processing for mining social media for newsgathering and discuss five different areas that researchers have worked on to mitigate the challenges inherent to social media news gathering: news discovery, curation of news, validation and verification of content, news gathering dashboards, and other tasks.