{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:20:21Z","timestamp":1777890021047,"version":"3.51.4"},"reference-count":69,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SW"],"published-print":{"date-parts":[[2023,5,8]]},"abstract":"<jats:p>Social networks have become information dissemination channels, where announcements are posted frequently; they also serve as frameworks for debates in various areas (e.g., scientific, political, and social). In particular, in the health area, social networks represent a channel to communicate and disseminate novel treatments\u2019 success; they also allow ordinary people to express their concerns about a disease or disorder. The Artificial Intelligence (AI) community has developed analytical methods to uncover and predict patterns from posts that enable it to explain news about a particular topic, e.g., mental disorders expressed as eating disorders or depression. Albeit potentially rich while expressing an idea or concern, posts are presented as short texts, preventing, thus, AI models from accurately encoding these posts\u2019 contextual knowledge. We propose a hybrid approach where knowledge encoded in community-maintained knowledge graphs (e.g., Wikidata) is combined with deep learning to categorize social media posts using existing classification models. The proposed approach resorts to state-of-the-art named entity recognizers and linkers (e.g., Falcon 2.0) to extract entities in short posts and link them to concepts in knowledge graphs. Then, knowledge graph embeddings (KGEs) are utilized to compute latent representations of the extracted entities, which result in vector representations of the posts that encode these entities\u2019 contextual knowledge extracted from the knowledge graphs. These KGEs are combined with contextualized word embeddings (e.g., BERT) to generate a context-based representation of the posts that empower prediction models. We apply our proposed approach in the health domain to detect whether a publication is related to an eating disorder (e.g., anorexia or bulimia) and uncover concepts within the discourse that could help healthcare providers diagnose this type of mental disorder. We evaluate our approach on a dataset of 2,000 tweets about eating disorders. Our experimental results suggest that combining contextual knowledge encoded in word embeddings with the one built from knowledge graphs increases the reliability of the predictive models. The ambition is that the proposed method can support health domain experts in discovering patterns that may forecast a mental disorder, enhancing early detection and more precise diagnosis towards personalized medicine.<\/jats:p>","DOI":"10.3233\/sw-223269","type":"journal-article","created":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T12:15:02Z","timestamp":1678796102000},"page":"873-892","source":"Crossref","is-referenced-by-count":11,"title":["Empowering machine learning models with contextual knowledge for enhancing the detection of eating disorders in social media\u00a0posts"],"prefix":"10.1177","volume":"14","author":[{"given":"Jos\u00e9 Alberto","family":"Ben\u00edtez-Andrades","sequence":"first","affiliation":[{"name":"SALBIS Research Group, Department of Electric, Systems and Automatics Engineering, Universidad de Le\u00f3n, Le\u00f3n, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mar\u00eda Teresa","family":"Garc\u00eda-Ord\u00e1s","sequence":"additional","affiliation":[{"name":"SECOMUCI Research Group, Escuela de Ingenier\u00edas Industrial e Inform\u00e1tica, Universidad de Le\u00f3n,Le\u00f3n, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayra","family":"Russo","sequence":"additional","affiliation":[{"name":"Leibniz University of Hannover and L3S Research Center and TIB Leibniz Information Centre for Science and Technology, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmad","family":"Sakor","sequence":"additional","affiliation":[{"name":"Leibniz University of Hannover and L3S Research Center and TIB Leibniz Information Centre for Science and Technology, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luis Daniel","family":"Fernandes Rotger","sequence":"additional","affiliation":[{"name":"Bakken and\u00a0Baeck GmbH, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria-Esther","family":"Vidal","sequence":"additional","affiliation":[{"name":"Leibniz University of Hannover and L3S Research Center and TIB Leibniz Information Centre for Science and Technology, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"9","key":"10.3233\/SW-223269_ref1","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1080\/1206212X.2021.1957551","article-title":"An intelligent approach for mining knowledge graphs of online news","volume":"44","author":"Abhishek","year":"2022","journal-title":"International Journal of Computers and Applications"},{"issue":"8","key":"10.3233\/SW-223269_ref2","doi-asserted-by":"publisher","first-page":"5789","DOI":"10.1007\/s10462-021-09958-2","article-title":"Transformer models for text-based emotion detection: A review of BERT-based approaches","volume":"54","author":"Acheampong","year":"2021","journal-title":"Artificial Intelligence Review"},{"key":"10.3233\/SW-223269_ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-55814-7_18"},{"key":"10.3233\/SW-223269_ref4","unstructured":"S.\u00a0Arora, Y.\u00a0Liang and T.\u00a0Ma, A simple but tough-to-beat baseline for sentence embeddings, in: ICLR, 2017."},{"key":"10.3233\/SW-223269_ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1526993.1526995"},{"issue":"6","key":"10.3233\/SW-223269_ref6","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1145\/3209581","article-title":"Bias on the web","volume":"61","author":"Baeza-Yates","year":"2018","journal-title":"Commun. ACM"},{"key":"10.3233\/SW-223269_ref7","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.7101682"},{"key":"10.3233\/SW-223269_ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS52027.2021.00105"},{"issue":"2","key":"10.3233\/SW-223269_ref9","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1080\/09638237.2019.1677878","article-title":"Mental illness and bipolar disorder on Twitter: Implications for stigma and social support","volume":"29","author":"Budenz","year":"2020","journal-title":"Journal of Mental Health"},{"key":"10.3233\/SW-223269_ref11","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.jnca.2017.01.029","article-title":"T-Hoarder: A framework to process Twitter data streams","volume":"83","author":"Congosto","year":"2017","journal-title":"Journal of Network and Computer Applications"},{"key":"10.3233\/SW-223269_ref12","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.copsyc.2016.01.004","article-title":"Social media, big data, and mental health: Current advances and ethical implications","volume":"9","author":"Conway","year":"2016","journal-title":"Current Opinion in Psychology"},{"key":"10.3233\/SW-223269_ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-9326-7_5"},{"key":"10.3233\/SW-223269_ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"10.3233\/SW-223269_ref16","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n1787"},{"key":"10.3233\/SW-223269_ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.105968"},{"issue":"1","key":"10.3233\/SW-223269_ref18","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MIC.2020.3031769","article-title":"Semantics of the black-box: Can knowledge graphs help make deep learning systems more interpretable and explainable?","volume":"25","author":"Gaur","year":"2021","journal-title":"IEEE Internet Computing"},{"key":"10.3233\/SW-223269_ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11920-019-1094-0"},{"key":"10.3233\/SW-223269_ref21","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/3604113"},{"issue":"3","key":"10.3233\/SW-223269_ref22","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1145\/3418294","article-title":"Knowledge graphs","volume":"64","author":"Guti\u00e9rrez","year":"2021","journal-title":"Communications of the ACM"},{"key":"10.3233\/SW-223269_ref23","doi-asserted-by":"publisher","DOI":"10.5888\/pcd15.170309"},{"key":"10.3233\/SW-223269_ref24","doi-asserted-by":"publisher","DOI":"10.2196\/35928"},{"key":"10.3233\/SW-223269_ref25","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2016.7841081"},{"key":"10.3233\/SW-223269_ref27","unstructured":"L.C.\u00a0Jain and L.R.\u00a0Medsker, Recurrent Neural Networks: Design and Applications, 1st edn, CRC Press, Inc., USA, 1999. ISBN: 0849371813."},{"key":"10.3233\/SW-223269_ref28","doi-asserted-by":"publisher","DOI":"10.3390\/app10175841"},{"key":"10.3233\/SW-223269_ref29","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.7224"},{"key":"10.3233\/SW-223269_ref30","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2018.00024"},{"key":"10.3233\/SW-223269_ref32","unstructured":"H.\u00a0Le, L.\u00a0Vial, J.\u00a0Frej, V.\u00a0Segonne, M.\u00a0Coavoux, B.\u00a0Lecouteux, A.\u00a0Allauzen, B.\u00a0Crabb\u00e9, L.\u00a0Besacier and D.\u00a0Schwab, FlauBERT: Unsupervised language model pre-training for French, in: Proceedings of the 12th Language Resources and Evaluation Conference, European Language Resources Association, Marseille, France, 2020, pp.\u00a02479\u20132490. https:\/\/www.aclweb.org\/anthology\/2020.lrec-1.302."},{"issue":"2","key":"10.3233\/SW-223269_ref33","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3233\/SW-140134","article-title":"DBpedia \u2013 A large-scale, multilingual knowledge base extracted from Wikipedia","volume":"6","author":"Lehmann","year":"2015","journal-title":"Semantic Web"},{"key":"10.3233\/SW-223269_ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3532577"},{"key":"10.3233\/SW-223269_ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-020-00128-2"},{"key":"10.3233\/SW-223269_ref38","doi-asserted-by":"publisher","DOI":"10.3390\/app11041838"},{"issue":"5","key":"10.3233\/SW-223269_ref39","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1080\/01612840.2020.1814914","article-title":"Mental health discourses on Twitter during mental health awareness week","volume":"42","author":"Makita","year":"2021","journal-title":"Issues in Mental Health Nursing"},{"key":"10.3233\/SW-223269_ref40","first-page":"8","article-title":"#Eating disorders and Instagram: What emotions do you express?","author":"Malighetti","year":"2020","journal-title":"Annual Review of Cybertherapy and Telemedicine"},{"key":"10.3233\/SW-223269_ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00668-6_23"},{"key":"10.3233\/SW-223269_ref42","doi-asserted-by":"crossref","unstructured":"L.\u00a0Martin, B.\u00a0Muller, P.J.O.\u00a0Su\u00e1rez, Y.\u00a0Dupont, L.\u00a0Romary, \u00c9.V.\u00a0de la Clergerie, D.\u00a0Seddah and B.\u00a0Sagot, CamemBERT: A tasty French language model, in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020.","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"10.3233\/SW-223269_ref43","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.926709"},{"key":"10.3233\/SW-223269_ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.2"},{"key":"10.3233\/SW-223269_ref46","doi-asserted-by":"publisher","DOI":"10.2196\/26011"},{"key":"10.3233\/SW-223269_ref48","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2019.00013"},{"key":"10.3233\/SW-223269_ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06245-2_10"},{"key":"10.3233\/SW-223269_ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3462462.3468881"},{"key":"10.3233\/SW-223269_ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107393"},{"key":"10.3233\/SW-223269_ref52","doi-asserted-by":"publisher","first-page":"3123","DOI":"10.1007\/s11063-020-10312-w","article-title":"Combining embeddings of input data for text classification","volume":"53","author":"Parcheta","year":"2021","journal-title":"Neural Processing Letters"},{"key":"10.3233\/SW-223269_ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300881"},{"key":"10.3233\/SW-223269_ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98305-5"},{"key":"10.3233\/SW-223269_ref56","doi-asserted-by":"crossref","unstructured":"P.\u00a0Ristoski and H.\u00a0Paulheim, RDF2Vec: RDF graph embeddings for data mining, in: SEMWEB, 2016.","DOI":"10.1007\/978-3-319-46523-4_30"},{"issue":"3","key":"10.3233\/SW-223269_ref57","doi-asserted-by":"publisher","first-page":"234","DOI":"10.2174\/157489312802460721","article-title":"Towards an ontology to support semantics enabled diagnostic decision support systems","volume":"7","author":"Rodriguez-Gonzalez","year":"2012","journal-title":"Current Bioinformatics"},{"key":"10.3233\/SW-223269_ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412777"},{"key":"10.3233\/SW-223269_ref60","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1016\/S0140-6736(21)02143-7","article-title":"Global prevalence and burden of depressive and anxiety disorders in 204 countries and territories in 2020 due to the COVID-19 pandemic","volume":"398","author":"Santomauro","year":"2021","journal-title":"The Lancet"},{"key":"10.3233\/SW-223269_ref61","unstructured":"S.D.M.G.-\u00a0TIB, SDM-RDF2vec, GitHub, 2022."},{"key":"10.3233\/SW-223269_ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2020.113122"},{"issue":"6","key":"10.3233\/SW-223269_ref63","doi-asserted-by":"publisher","first-page":"129:1","DOI":"10.1145\/3422824","article-title":"Using social media for mental health surveillance: A review","volume":"53","author":"Skaik","year":"2020","journal-title":"ACM Computing Surveys"},{"key":"10.3233\/SW-223269_ref64","doi-asserted-by":"publisher","DOI":"10.3390\/fi13070163"},{"key":"10.3233\/SW-223269_ref65","doi-asserted-by":"publisher","DOI":"10.2196\/24340"},{"key":"10.3233\/SW-223269_ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-2514-4_36"},{"issue":"2","key":"10.3233\/SW-223269_ref67","doi-asserted-by":"publisher","first-page":"233","DOI":"10.3233\/SW-210444","article-title":"Representing COVID-19 information in collaborative knowledge graphs: The case of Wikidata","volume":"14","author":"Turki","year":"2022","journal-title":"Semantic Web"},{"key":"10.3233\/SW-223269_ref68","first-page":"57","article-title":"Fine and ultra-fine entity type embeddings for question answering","volume":"2774","author":"Vallurupalli","year":"2020","journal-title":"CEUR Workshop Proceedings"},{"key":"10.3233\/SW-223269_ref70","doi-asserted-by":"publisher","DOI":"10.2196\/17626"},{"issue":"10","key":"10.3233\/SW-223269_ref71","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","article-title":"Wikidata: A free collaborative knowledgebase","volume":"57","author":"Vrandecic","year":"2014","journal-title":"Commun. ACM"},{"key":"10.3233\/SW-223269_ref72","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.52614"},{"key":"10.3233\/SW-223269_ref73","doi-asserted-by":"publisher","DOI":"10.3390\/cancers11111673"},{"key":"10.3233\/SW-223269_ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018706"},{"key":"10.3233\/SW-223269_ref75","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-822201-0.00018-6"},{"key":"10.3233\/SW-223269_ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ISCIPT53667.2021.00164"},{"key":"10.3233\/SW-223269_ref77","doi-asserted-by":"publisher","DOI":"10.2196\/20550"},{"key":"10.3233\/SW-223269_ref78","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA200355"},{"key":"10.3233\/SW-223269_ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3440067.3440077"},{"key":"10.3233\/SW-223269_ref80","doi-asserted-by":"publisher","DOI":"10.2196\/18273"},{"key":"10.3233\/SW-223269_ref81","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/S2215-0366(21)00435-1","article-title":"The hidden burden of eating disorders during the COVID-19 pandemic","volume":"9","author":"Zipfel","year":"2022","journal-title":"The Lancet Psychiatry"}],"container-title":["Semantic Web"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/SW-223269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:26:49Z","timestamp":1777613209000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/SW-223269"}},"subtitle":[],"editor":[{"given":"Haridimos","family":"Kondylakis","sequence":"additional","affiliation":[{"name":"FORTH-ICS, Greece"}],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Praveen","family":"Rao","sequence":"additional","affiliation":[{"name":"University of Missouri, USA"}],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Kostas","family":"Stefanidis","sequence":"additional","affiliation":[{"name":"Tampere University, Finland"}],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Kostas","family":"Stefanidis","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Haridimos","family":"Kondylakis","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Praveen","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":69,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/sw-223269","relation":{},"ISSN":["2210-4968","1570-0844"],"issn-type":[{"value":"2210-4968","type":"electronic"},{"value":"1570-0844","type":"print"}],"subject":[],"published":{"date-parts":[[2023,5,8]]}}}