Call for Participation - TREC Health Misinformation Track 2022 https://trec-health-misinfo.github.io
Overview π§ -------------------------- Web search engines are frequently used to help people make decisions about health-related issues. Unfortunately, the web is filled with misinformation regarding the efficacy of treatments for health issues. Search users may not be able to discern correct from incorrect information, nor credible from non-credible sources. As a result of finding misinformation deemed by the user to be useful to their decision making task, they can make incorrect decisions that waste money and put their health at risk. The TREC Health Misinformation track fosters research on retrieval methods that promote reliable and correct information over misinformation for health-related decision making tasks. Tasks πΌ -------------------------- * Ad-hoc Retrieval Task: design a ranking model that promotes credible and correct information over incorrect information; * Answer Prediction Task: predict the answer to the topicβs stance. Guidelines π -------------------------- * Corpus: noclean version of the C4 dataset (https://huggingface.co/datasets/allenai/c4); * Topics: about consumer health search (people seeking health advice online); * Runs: runs may be either automatic or manual with the standard TREC run format. Detailed guidelines: https://trec-health-misinfo.github.io Important Dates π₯ -------------------------- * Runs due from participants: August 28, 2022 * Evaluation results returned: End of September 2022 * Notebook paper due: October 2022 * TREC 2022 Conference: November 14-18, 2022 * Final paper due: February 2023 Organization π -------------------------- * Charles Clarke, University of Waterloo * Maria Maistro, University of Copenhagen * Mark Smucker, University of Waterloo βββ Maria Maistro, PhD Tenure-track Assistant Professor Department of Computer Science University of Copenhagen Universitetsparken 5, 2100 Copenhagen, Denmark
_______________________________________________ Corpora mailing list -- [email protected] https://list.elra.info/mailman3/postorius/lists/corpora.list.elra.info/ To unsubscribe send an email to [email protected]
