An evaluation of keyword extraction from online communication for the\n characterisation of social relations

2014/02/11 by Jan Hauffa, Hauffa, Jan, Tobias Lichtenberg +3
Computer Science · #Advanced Text Analysis Techniques

paper · pdf · doi:10.48550/arxiv.1402.2427

Abstract

The set of interpersonal relationships on a social network service or a\nsimilar online community is usually highly heterogenous. The concept of tie\nstrength captures only one aspect of this heterogeneity. Since the unstructured\ntext content of online communication artefacts is a salient source of\ninformation about a social relationship, we investigate the utility of keywords\nextracted from the message body as a representation of the relationship's\ncharacteristics as reflected by the conversation topics. Keyword extraction is\nperformed using standard natural language processing methods. Communication\ndata and human assessments of the extracted keywords are obtained from Facebook\nusers via a custom application. The overall positive quality assessment\nprovides evidence that the keywords indeed convey relevant information about\nthe relationship.\n

Citations

• The Strength of Weak Ties

Related

• Structure vs. Language: Investigating the Multi-factors of Asymmetric Opinions on Online Social Interrelationship with a Case Study
• Keyword Extraction for Identifying Social Actors
• Implications of construction decisions in keyword-based networks: an empirical assessment
• Romantic partnerships and the dispersion of social ties
• The Four Dimensions of Social Network Analysis: An Overview of Research\n Methods, Applications, and Software Tools