Webis Health CauseNet 2022

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 Health 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. <pre><code>@InProceedings{schlatt2022health-causenet, author = {Ferdinand Schlatt and Dieter Bettin and Matthias Hagen and Benno Stein and Martin Potthast}, booktitle = {29th International Conference on Computational Linguistics (COLING 2022)}, publisher = {Association for Computational Linguistics}, site = {Gyeongju, Republic of Korea}, title = {{Mining Health-related Cause-Effect Statements with High Precision at Large Scale}}, year = 2022 } </code></pre>在大规模挖掘网页以开展健康社会学分析、或是开发健康搜索引擎的场景中，高效评估文本段落与健康的关联度至关重要。我们提出了一种全新的高效术语度评分（termhood score）方法，用于预测短语与句子的健康关联度。该方法在包含因果陈述的网页数据集上，可在超过90%的精确率（precision）下实现69%的召回率（recall）。其性能优于当前最优（state-of-the-art）的医疗实体链接器（medical entity linkers），与基于BERT的方法（BERT-based approaches）效果相当，但运行速度大幅更快。我们依托该方法构建了Webis健康因果网络2022（Webis Health CauseNet 2022），这是一个包含780万条健康相关因果陈述的全新数据集，例如「研究表明压力会引发失眠」，其中因果关系（「压力」为因，「失眠」为果）均已完成标注。 <pre><code>@InProceedings{schlatt2022health-causenet, author = {Ferdinand Schlatt and Dieter Bettin and Matthias Hagen and Benno Stein and Martin Potthast}, booktitle = {29th International Conference on Computational Linguistics (COLING 2022)}, publisher = {Association for Computational Linguistics}, site = {Gyeongju, Republic of Korea}, title = {{Mining Health-related Cause-Effect Statements with High Precision at Large Scale}}, year = 2022 }</code></pre>