A Framework for Real-time Semantic Social Media Analysis

Diana Maynard, Ian Roberts, Mark A. Greenwood, Dominic Rout, Kalina Bontcheva


This paper presents a framework for collecting and analysing large volume social media content. The real-time analytics framework comprises semantic annotation, Linked Open Data, semantic search, and dynamic result aggregation components. In addition, exploratory search and sense-making are supported through information visualisation interfaces, such as co-occurrence matrices, term clouds, treemaps, and choropleths. There is also an interactive semantic search interface (Prospector), where users can save, refine, and analyse the results of semantic search queries over time. Practical use of the framework is exemplified through three case studies: a general scenario analysing tweets from UK politicians and the public’s response to them in the run up to the 2015 UK general election, an investigation of attitudes towards climate change expressed by these politicians and the public, via their engagement with environmental topics, and an analysis of public tweets leading up to the UK’s referendum on leaving the EU (Brexit) in 2016. The paper also presents a brief evaluation and discussion of some of the key text analysis components, which are specifically adapted to the domain and task, and demonstrate scalability and eciency of our toolkit in the case studies.

Full Text: Untitled
Type of Paper: Research Paper
Keywords: Natural Language Processing, semantic search, social media analysis, Linked Open Data, semantic annotation, sentiment analysis
Show BibTex format: BibTeX