%0 Conference Paper %1 schlatt-etal-2022-mining %A Schlatt, Ferdinand %A Bettin, Dieter %A Hagen, Matthias %A Stein, Benno %A Potthast, Martin %B Proceedings of the 29th International Conference on Computational Linguistics %C Gyeongju, Republic of Korea %D 2022 %I International Committee on Computational Linguistics %K topic_language %P 1925--1936 %T Mining Health-related Cause-Effect Statements with High Precision at Large Scale %U https://aclanthology.org/2022.coling-1.167 %X An efficient assessment of the health relatedness of text passages is important to mine the web at scale to conduct health sociological analyses or to develop a health search engine. We propose a new efficient and effective termhood score for predicting the health relatedness of phrases and sentences, which achieves 69\% recall at over 90\% precision on a web dataset with cause-effect statements. It is more effective than state-of-the-art medical entity linkers and as effective but much faster than BERT-based approaches. Using our method, we compile the Webis Medical CauseNet 2022, a new resource of 7.8 million health-related cause-effect statements such as ``Studies show that stress induces insomnia'' in which the cause (`stress') and effect (`insomnia') are labeled.

@inproceedings{schlatt-etal-2022-mining, abstract = {An efficient assessment of the health relatedness of text passages is important to mine the web at scale to conduct health sociological analyses or to develop a health search engine. We propose a new efficient and effective termhood score for predicting the health relatedness of phrases and sentences, which achieves 69{\%} recall at over 90{\%} precision on a web dataset with cause-effect statements. It is more effective than state-of-the-art medical entity linkers and as effective but much faster than BERT-based approaches. Using our method, we compile the Webis Medical CauseNet 2022, a new resource of 7.8 million health-related cause-effect statements such as {``}Studies show that stress induces insomnia{''} in which the cause ({`}stress{'}) and effect ({`}insomnia{'}) are labeled.}, added-at = {2024-09-10T11:56:37.000+0200}, address = {Gyeongju, Republic of Korea}, author = {Schlatt, Ferdinand and Bettin, Dieter and Hagen, Matthias and Stein, Benno and Potthast, Martin}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/224968373f9372cf91b290970d354b8f8/scadsfct}, booktitle = {Proceedings of the 29th International Conference on Computational Linguistics}, interhash = {d53f3284a009585ce724b97abe75e1bc}, intrahash = {24968373f9372cf91b290970d354b8f8}, keywords = {topic_language}, month = oct, pages = {1925--1936}, publisher = {International Committee on Computational Linguistics}, timestamp = {2024-11-22T15:47:33.000+0100}, title = {Mining Health-related Cause-Effect Statements with High Precision at Large Scale}, url = {https://aclanthology.org/2022.coling-1.167}, year = 2022 }