Topological and topical characterisation of Twitter user communities

Abstract

Purpose Most of the existing literature on online social networks (OSNs) either focuses on community detection in graphs without considering the topic of the messages exchanged, or concentrates exclusively on the messages without taking into account the social links. The purpose of this paper is to characterise the semantic cohesion of such groups through the introduction of new measures. Design/methodology/approach A theoretical model for social links and salient topics on Twitter is proposed. Also, measures to evaluate the topical cohesiveness of a group are introduced. Inspired from precision and recall, the proposed measures, called expertise and representativeness, assess how a set of groups match the topic distribution. An adapted measure is also introduced when a topic similarity can be computed. Finally, a topic relevance measure is defined, similar to tf.idf (term-frequency, inverse document frequency). Findings The measures yield interesting results, notably on a large tweet corpus: the metrics accurately describe the topics discussed in the tweets and enable to identify topic-focused groups. Combined with topological measures, they provide a global and concise view of the detected groups. Originality/value Many algorithms, applied on OSN, detect communities which often lack of meaning and internal semantic cohesion. This paper is among the first to quantify this aspect, and more precisely the topical cohesion and topical relevance of a group. Moreover, the proposed indicators can be exploited for social media monitoring, to investigate the impact of a group of people: for instance, they could be used for journalism, marketing and security purposes.

Network Platform for Tourism Sector: Transformation and Interpretation of Multifaceted Data

“…These include tourism [1], commuting [2], exchanging [3]-exercises associated with voyages moreover are displayed by systems consistently. Similar sociable contacts [4,5] and relevant spread structures for data and contaminations [6] are of the same profile. Such frameworks and information represent the entities that are described by network-like data (NLD) [7].…”

Study on the interaction between big data and artificial intelligence

“…AI techniques can extract intelligence from posted messages, qualify the user behaviours, and identify the social structure, which addresses the exploitation difficult due to the quantity of information. In Gadek et al's (2018) work, they illustrate how to exploit AI on a very peculiar social network, named Ga‐laxy2, by proposing an analysis of 1000 days of activity using NLP techniques to find the most interesting topics and to discover key actors. Then they proceed with a machine learning‐based profiling of the user behaviours and introduce influence and cohesion scores for groups of users, which help characterization and evaluation.…”

A complex network analysis of the Comprehensive R Archive Network (CRAN) package ecosystem

“…In general, one of the many challenges proposed in the field of complex network analysis consists of community detection, and multiple community detection algorithms have been described (Gadek et al, 2018). One of the most popular and widely used algorithm is the Louvain method (Blondel et al, 2008), which maximizes a modularity score for each community.…”