Automatic evaluation of information provider reliability and expertise

Abstract

Q&A social media have gained a lot of attention during the recent years. People rely on these sites to obtain information due to a number of advantages they offer as compared to conventional sources of knowledge (e.g., asynchronous and convenient access). However, for the same question one may find highly contradicting answers, causing an ambiguity with respect to the correct information. This can be attributed to the presence of unreliable and/or non-expert users. These two attributes (reliability and expertise) significantly affect the quality of the answer/information provided. We present a novel approach for estimating these user's characteristics relying on human cognitive traits. In brief, we propose each user to monitor the activity of his peers (on the basis of responses to questions asked by him) and observe their compliance with predefined cognitive models. These observations lead to local assessments that can be further fused to obtain a reliability and expertise consensus for every other user in the social network (SN). For the aggregation part we use subjective logic. To the best of our knowledge this is the first study of this kind in the context of Q&A SNs. Our proposed approach is highly distributed; each user can individually estimate the expertise and the reliability of his peers using his direct interactions with them and our framework. The online SN (OSN), which can be considered as a distributed database, performs continuous data aggregation for users expertise and reliability assesment in order to reach a consensus. In our evaluations, we first emulate a Q&A SN to examine various performance aspects of our algorithm (e.g., convergence time, responsiveness etc.). Our evaluations indicate that it can accurately assess the reliability and the expertise of a user with a small number of samples and can successfully react to the latter's behavior change, provided that the cognitive traits hold in practice. Furthermore, the use of the consensus operator for the aggregation of multiple opinions on a specific user, reduces the uncertainty with regards to the final assessment. However, as real data obtained from Yahoo! Answers imply, the pairwise interactions between specific users are limited. Hence, we consider the aggregate set of questions as posted from the system itself and we assess the expertise and realibility of users based on their response behavior. We observe, that users have different behaviors depending on the level at which we are observing them. In particular, while their activity is focused on a few general categories, yielding them reliable, their microscopic (within general category) activity is highly scattered.

Fake News Detection Based on Subjective Opinions

“…To the best of our knowledge, this work is the first to apply Subjective Opinions to the area of fake news detection. Before this, it is widely used in many other areas, including trust network analysis [31], conditional inference [32], information provider reliability assessment [33], trust management in sensor networks [34]. In one of our earlier works [35], Subjective Opinions is introduced for Truth Discovery.…”

SLFTD: A Subjective Logic Based Framework for Truth Discovery

“…Subjective Logic [12,13] is a powerful decision making tool extending the probabilistic logic by including uncertainty and subjective belief ownership. It is widely used in trust network analysis [14], conditional inference [15], information provider reliability assessment [16], trust management in sensor networks [17], etc. Subjective logic uses subjective opinions to express subjective beliefs about the truth of propositions with degrees of uncertainty.…”

“…Though several algorithms haven proposed in this area, but their performance show large difference in different truth discovery scenarios. Also, there is no "onefits-all" model appearing, different dataset shows different best methods [16]. This motivates us to propose a generalized framework, that can be efficiently adapted to different truth discovery scenarios with less effort but relatively more stable performance.…”

Addressing the Terms-of-Service Threat - Client-side Security and Policy Control for Free File Storage Services

“…There are ways of assessing trust in an online context. We approaches such as the one laid out in (Pelechrinis et al, 2011) with automated evaluation of Q&A sessions over so-called online social networks (OSN). Reputation is keyword here and there are formalized approaches that directly uses reputation in the model (Jøsang, 2010).…”

“…The reputation manager will use methods discussed in (Jøsang, 2010;Pelechrinis et al, 2011) to extract information about the reliability and trustworthiness of the SP. The work in (Pelechrinis et al, 2011) will need to be extended to achieve full "reputation" handling. We do not further develop the reputation manager concept in this paper.…”