Overview of the CLEF eHealth Evaluation Lab 2021

Suominen, Hanna; Goeuriot, Lorraine; Kelly, Liadh; Alemany, Laura Alonso; Bassani, Elias; Brew‐Sam, Nicola; Cotik, Viviana; Filippo, Darío; González-Sáez, Gabriela; Luque, Franco M.; Mulhem, Philippe; Pasi, Gabriella; Roller, Roland; Seneviratne, Sandaru; Upadhyay, Rishabh; Vivaldi, Jorge; Viviani, Marco; Xu, Chenchen

doi:10.1007/978-3-030-85251-1_21

Cited by 8 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this reason, too, efforts are being made in recent years to address the problem of online misinformation by developing Information Retrieval Systems (IRS) that produce a ranked list of results that meet a user's information need while trying to uprank truthful results (Clarke et al, 2020;Pradeep et al, 2021;Suominen et al, 2021;Upadhyay et al, 2022). Such systems are relevant to our work as they do not produce a strict truthfulness judgment (used for binary classification), leaving the final decision to the user based on their investigation of the ranked list.…”

Section: Explainability In Tackling Online Misinformationmentioning

confidence: 99%

“…Hence, the purpose of this paper is precisely to address these issues in the context of ensuring user access to truthful information in the field of health. First of all, in order to avoid filtering information on the basis of its predicted truthfulness, the problem is studied in the context of the Information Retrieval (IR) task, and more specifically in that of Consumer Health Search (CHS), i.e., the search for health information by people without special medical expertise (Suominen et al, 2021 ). Additionally, the aim of this paper is to address the issue of explainability of search results in terms of information truthfulness.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Explainable online health information truthfulness in Consumer Health Search

Upadhyay

Knoth

Pasi

et al. 2023

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

IntroductionPeople are today increasingly relying on health information they find online to make decisions that may impact both their physical and mental wellbeing. Therefore, there is a growing need for systems that can assess the truthfulness of such health information. Most of the current literature solutions use machine learning or knowledge-based approaches treating the problem as a binary classification task, discriminating between correct information and misinformation. Such solutions present several problems with regard to user decision making, among which: (i) the binary classification task provides users with just two predetermined possibilities with respect to the truthfulness of the information, which users should take for granted; indeed, (ii) the processes by which the results were obtained are often opaque and the results themselves have little or no interpretation.MethodsTo address these issues, we approach the problem as an ad hoc retrieval task rather than a classification task, with reference, in particular, to the Consumer Health Search task. To do this, a previously proposed Information Retrieval model, which considers information truthfulness as a dimension of relevance, is used to obtain a ranked list of both topically-relevant and truthful documents. The novelty of this work concerns the extension of such a model with a solution for the explainability of the results obtained, by relying on a knowledge base consisting of scientific evidence in the form of medical journal articles.Results and discussionWe evaluate the proposed solution both quantitatively, as a standard classification task, and qualitatively, through a user study to examine the “explained” ranked list of documents. The results obtained illustrate the solution's effectiveness and usefulness in making the retrieved results more interpretable by Consumer Health Searchers, both with respect to topical relevance and truthfulness.

show abstract

Section: Explainability In Tackling Online Misinformationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%