Information Intermediaries and Information Resilience: Working to Support Marginalised Groups

Information resilience has become a topic of interest to the information science community in recent years. The COVID-19 pandemic has shone a light on the vulnerability of information and other networks and the impact on information providers and the information seekers who rely on them. In an exploratory study, we interviewed support workers who act as information intermediaries as part of their work roles about their experiences of providing information to vulnerable and marginalised people during the UK COVID-19 lockdown. We present findings organised in three themes: shifting client information needs and support provisions, adjusting information sharing and communication practices and workarounds for physical information work. Throughout the themes, information resilience is evident as information intermediaries adapt their work practices to ensure they can continue to serve their clients. In this first stage of research our findings provide insight into the changes to information intermediaries' information behaviour and information work during a crisis, as well as the impact of these changes on the services they provide. 85th Annual Meeting of the Association for Information Science & Technology ;Oct. 29 – Nov. 1, 2022 ;Pittsburgh, PA. Author(s) retain copyright, but ASIS&T receives an exclusive publication license.

Comparing Traditional and Neural Approaches for Detecting Health-Related Misinformation

Detecting health-related misinformation is a research challenge that has recently received increasing attention. Helping people to find credible and accurate health information on the Web remains an open research issue as has been highlighted during the COVID-19 pandemic. However, in such scenarios, it is often critical to detect misinformation quickly [34], which implies working with little data, at least at the beginning of the spread of such information. In this work, we present a comparison between different automatic approaches of identifying misinformation, and we compare how they behave for different tasks and with limited training data. We experiment with traditional algorithms, such as SVMs or KNNs, as well as newer BERT-based models [5]. Our experiments utilise the CLEF 2018 Consumer Health Search task dataset [16] to perform experiments on detecting untrustworthy contents and information that is difficult to read. Our results suggest that traditional models are still a strong baseline for these challenging tasks. In the absence of substantive training data, classical approaches tend to outperform BERT-based models. © 2021, Springer Nature Switzerland AG.

Reliability Prediction for Health-Related Content: A Replicability Study

Determining reliability of online data is a challenge that has recently received increasing attention. In particular, unreliable health-related content has become pervasive during the COVID-19 pandemic. Previous research [37] has approached this problem with standard classification technology using a set of features that have included linguistic and external variables, among others. In this work, we aim to replicate parts of the study conducted by Sondhi and his colleagues using our own code, and make it available for the research community (https://github.com/MarcosFP97/Health-Rel ). The performance obtained in this study is as strong as the one reported by the original authors. Moreover, their conclusions are also confirmed by our replicability study. We report on the challenges involved in replication, including that it was impossible to replicate the computation of some features (since some tools or services originally used are now outdated or unavailable). Finally, we also report on a generalisation effort made to evaluate our predictive technology over new datasets [20, 35]. © 2021, Springer Nature Switzerland AG.