Content feature enrichment for analyzing trust relationships in web forums

Abstract

As criminals and terrorist employ social media platforms for planning and executing nefarious activities, understanding the degree of trustworthiness in interactions among actors becomes crucial for detecting their activities. Measuring trust in these environments can benefit analysts who are monitoring web forums to detect criminal or terrorist activities. Previous research proposed a trust model that could enable automatic trust discovery using speech act theory. This paper introduces a new classification method that enriches traditional techniques with contextual information. We conducted experiments to compare the proposed method with traditional approaches. The results show that the proposed method outperforms other alternative methods.

Towards building general framework for designing knowledge sharing tool based on actor network theory

“…For the interest assessment, the focal actor (MKSS) negotiates that the 12 actors as the essential items in the actor-network to deliver the needs of KS activities; hence, MKSS must have the mechanism to trace and detect the presence of the 12 actors' activities. For example, MKSS has a mechanism to trace the existence of trust within online communities using some intelligent techniques such as text processing technique (Piorkowski and Zhou, 2011) or to identify the presence of certain network structure by performing the link analysis (McNutt, 2006). Enrolment is the process of making the 12 actors to its commitment, while mobilization is the state where the actors are ready to perform the duties; the details are described in Figure 5.…”

Data mining techniques in social media: A survey

“…A20 Classifying ecommerce information sharing behaviour by youths on social networking sites 2011 [38] A21 Clustering memes in social media 2013 [39] A22 Collaborative filtering based on collaborative tagging for enhancing the quality of recommendation 2010 [40] A23 Collaborative visual modeling for automatic image annotation via sparse model coding 2012 [41] A24 Confucius and its intelligent disciples: integrating social with search 2010 [42] A25 Content Feature Enrichment for Analyzing Trust Relationships in Web Forums 2013 [43] A26 Content Matters : A study of hate groups detection based on social networks analysis and web mining 2013 [44] A27 Co-training over Domain-independent and Domain-dependent features for sentiment analysis of an online cancer support community 2013 [45] A28 Data-Mining Twitter and the Autism Spectrum Disorder : A Pilot Study 2014 [46] A29 Decision Fusion for Multimodal Biometrics Using Social Network Analysis 2014 [47] A30 Detecting Deception in Online Social Networks 2014 [48] A31 Enhancing financial performance with social media: An impression management perspective 2013 [49] A32 Enriching short text representation in microblog for clustering 2012 [50] A33 Estimating the helpfulness and economic impact of product reviews: Mining text and reviewer characteristics 2011 [51] A34 A56 The potential of social media in delivering transport policy goals 2014 [74] A57 The social media genome: modeling individual topic-specific behavior in social media 2013 [75] A58 Topic-sensitive influencer mining in interest-based social media networks via hypergraph learning 2014 [76] A59 Twitter, MySpace, Digg: Unsupervised Sentiment Analysis in Social Media 2012 [77] A60 Unsupervised and supervised learning to evaluate event relatedness based on content mining from socialmedia streams 2012 [78] A61 Using explicit linguistic expressions of preference in social media to predict voting behavior 2013 [79] A62 Using inter-comment similarity for comment spam detection in Chinese blogs 2011 [80] A63 Using Sentiment to Detect Bots on Twitter: Are Humans more Opinionated than Bots? 2014 [81] A64 Using social media to enhance emergency situation awareness 2012 [82] A65 Web data extraction, applications and techniques: A survey 2014 [83] A66 What's in twitter: I know what part...…”