You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP. Del Tredici, M., Marcheggiani, D., Schulte im Walde, S., & Fernández, R. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4707–4717, Hong Kong, China, November, 2019. Association for Computational Linguistics. ![You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex 1 download Information about individuals can help to better understand what they say, particularly in social media where texts are short. Current approaches to modelling social media users pay attention to their social connections, but exploit this information in a static way, treating all connections uniformly. This ignores the fact, well known in sociolinguistics, that an individual may be part of several communities which are not equally relevant in all communicative situations. We present a model based on Graph Attention Networks that captures this observation. It dynamically explores the social graph of a user, computes a user representation given the most relevant connections for a target task, and combines it with linguistic information to make a prediction. We apply our model to three different tasks, evaluate it against alternative models, and analyse the results extensively, showing that it significantly outperforms other current methods.
@inproceedings{del-tredici-etal-2019-shall,
title = "You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in {NLP}",
author = "Del Tredici, Marco and
Marcheggiani, Diego and
Schulte im Walde, Sabine and
Fern{\'a}ndez, Raquel",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1477.pdf",
doi = "10.18653/v1/D19-1477",
pages = "4707--4717",
abstract = "Information about individuals can help to better understand what they say, particularly in social media where texts are short. Current approaches to modelling social media users pay attention to their social connections, but exploit this information in a static way, treating all connections uniformly. This ignores the fact, well known in sociolinguistics, that an individual may be part of several communities which are not equally relevant in all communicative situations. We present a model based on Graph Attention Networks that captures this observation. It dynamically explores the social graph of a user, computes a user representation given the most relevant connections for a target task, and combines it with linguistic information to make a prediction. We apply our model to three different tasks, evaluate it against alternative models, and analyse the results extensively, showing that it significantly outperforms other current methods.",
}
Downloads: 1
{"_id":"ATiycDCY2uDeSP4eQ","bibbaseid":"deltredici-marcheggiani-schulteimwalde-fernndez-youshallknowauserbythecompanyitkeepsdynamicrepresentationsforsocialmediausersinnlp-2019","author_short":["Del Tredici, M.","Marcheggiani, D.","Schulte im Walde, S.","Fernández, R."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP","author":[{"propositions":[],"lastnames":["Del","Tredici"],"firstnames":["Marco"],"suffixes":[]},{"propositions":[],"lastnames":["Marcheggiani"],"firstnames":["Diego"],"suffixes":[]},{"propositions":["Schulte","im"],"lastnames":["Walde"],"firstnames":["Sabine"],"suffixes":[]},{"propositions":[],"lastnames":["Fernández"],"firstnames":["Raquel"],"suffixes":[]}],"booktitle":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","month":"November","year":"2019","address":"Hong Kong, China","publisher":"Association for Computational Linguistics","url":"https://aclanthology.org/D19-1477.pdf","doi":"10.18653/v1/D19-1477","pages":"4707–4717","abstract":"Information about individuals can help to better understand what they say, particularly in social media where texts are short. Current approaches to modelling social media users pay attention to their social connections, but exploit this information in a static way, treating all connections uniformly. This ignores the fact, well known in sociolinguistics, that an individual may be part of several communities which are not equally relevant in all communicative situations. We present a model based on Graph Attention Networks that captures this observation. It dynamically explores the social graph of a user, computes a user representation given the most relevant connections for a target task, and combines it with linguistic information to make a prediction. We apply our model to three different tasks, evaluate it against alternative models, and analyse the results extensively, showing that it significantly outperforms other current methods.","bibtex":"@inproceedings{del-tredici-etal-2019-shall,\n title = \"You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in {NLP}\",\n author = \"Del Tredici, Marco and\n Marcheggiani, Diego and\n Schulte im Walde, Sabine and\n Fern{\\'a}ndez, Raquel\",\n booktitle = \"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)\",\n month = nov,\n year = \"2019\",\n address = \"Hong Kong, China\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://aclanthology.org/D19-1477.pdf\",\n doi = \"10.18653/v1/D19-1477\",\n pages = \"4707--4717\",\n abstract = \"Information about individuals can help to better understand what they say, particularly in social media where texts are short. Current approaches to modelling social media users pay attention to their social connections, but exploit this information in a static way, treating all connections uniformly. This ignores the fact, well known in sociolinguistics, that an individual may be part of several communities which are not equally relevant in all communicative situations. We present a model based on Graph Attention Networks that captures this observation. It dynamically explores the social graph of a user, computes a user representation given the most relevant connections for a target task, and combines it with linguistic information to make a prediction. We apply our model to three different tasks, evaluate it against alternative models, and analyse the results extensively, showing that it significantly outperforms other current methods.\",\n}\n\n","author_short":["Del Tredici, M.","Marcheggiani, D.","Schulte im Walde, S.","Fernández, R."],"key":"del-tredici-etal-2019-shall","id":"del-tredici-etal-2019-shall","bibbaseid":"deltredici-marcheggiani-schulteimwalde-fernndez-youshallknowauserbythecompanyitkeepsdynamicrepresentationsforsocialmediausersinnlp-2019","role":"author","urls":{"Paper":"https://aclanthology.org/D19-1477.pdf"},"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/dmg-illc/dmg/master/bibbase/dmg-publications.bib","dataSources":["QzguzWy2fZZbXuFSd","8c2d6EwyPFHuHGcFK","42BzLCGMaDCpG5rq2","sXg85ARyqxCxh4Dnn"],"keywords":[],"search_terms":["shall","know","user","company","keeps","dynamic","representations","social","media","users","nlp","del tredici","marcheggiani","schulte im walde","fernández"],"title":"You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP","year":2019,"downloads":1}