Using semantic clustering to support situation awareness on Twitter: the case of world views

• Published in: Human-centric computing and information sciences Vol. 8; no. 1; pp. 1 - 31
• Main Authors: Kingston, Charlie, Nurse, Jason R. C., Agrafiotis, Ioannis, Milich, Andrew Burke
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 30.07.2018; Korea Information Processing Society, Computer Software Research Group
• Subjects: Artificial Intelligence; Clustering; Communications Engineering; Computer Science; Computer Systems Organization and Communication Networks; Data analysis; Decision making; Digital media; Information Systems and Communication Service; Information Systems Applications (incl.Internet); Networks; Semantics; Situational awareness; Social networks; User Interfaces and Human Computer Interaction; Social media analytics; Crisis response; Data clustering; User-support tools; Computational social science; Fake news; Information systems
• ISSN: 2192-1962; 2192-1962
• DOI: 10.1186/s13673-018-0145-6

In recent years, situation awareness has been recognised as a critical part of effective decision making, in particular for crisis management. One way to extract value and allow for better situation awareness is to develop a system capable of analysing a dataset of multiple posts, and clustering consistent posts into different views or stories (or, ‘world views’). However, this can be challenging as it requires an understanding of the data, including determining what is consistent data, and what data corroborates other data. Attempting to address these problems, this article proposes Subject-Verb-Object Semantic Suffix Tree Clustering (SVOSSTC) and a system to support it, with a special focus on Twitter content. The novelty and value of SVOSSTC is its emphasis on utilising the Subject–Verb–Object typology in order to construct semantically consistent world views, in which individuals—particularly those involved in crisis response—might achieve an enhanced picture of a situation from social media data. To evaluate our system and its ability to provide enhanced situation awareness, we tested it against existing approaches, including human data analysis, using a variety of real-world scenarios. The results indicated a noteworthy degree of evidence (e.g., in cluster granularity and meaningfulness) to affirm the suitability and rigour of our approach. Moreover, these results highlight this article’s proposals as innovative and practical system contributions to the research field.