{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T13:43:32Z","timestamp":1694785412188},"reference-count":20,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["AI Magazine"],"published-print":{"date-parts":[[2023,9]]},"abstract":"Abstract<\/jats:title>Our paper aims to analyze political polarization in US political system using language models, and thereby help candidates make an informed decision. The availability of this information will help voters understand their candidates' views on the economy, healthcare, education, and other social issues. Our main contributions are a dataset extracted from Wikipedia that spans the past 120 years and a language model\u2010based method that helps analyze how polarized a candidate is. Our data are divided into two parts, background information and political information about a candidate, since our hypothesis is that the political views of a candidate should be based on reason and be independent of factors such as birthplace, alma mater, and so forth. We further split this data into four phases chronologically, to help understand if and how the polarization amongst candidates changes. This data has been cleaned to remove biases. To understand the polarization, we begin by showing results from some classical language models in Word2Vec and Doc2Vec. And then use more powerful techniques like the Longformer, a transformer\u2010based encoder, to assimilate more information and find the nearest neighbors of each candidate based on their political view and their background. The code and data for the project will be available here: \u201chttps:\/\/github.com\/samirangode\/Understanding_Polarization<\/jats:ext-link>\u201d<\/jats:p>","DOI":"10.1002\/aaai.12104","type":"journal-article","created":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T08:11:19Z","timestamp":1691395879000},"page":"248-254","update-policy":"http:\/\/dx.doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Understanding political polarization using language models: A dataset and method"],"prefix":"10.1002","volume":"44","author":[{"ORCID":"http:\/\/orcid.org\/0009-0009-3324-9463","authenticated-orcid":false,"given":"Samiran","family":"Gode","sequence":"first","affiliation":[{"name":"Carnegie Mellon University Pittsburgh Pennsylvania USA"}]},{"given":"Supreeth","family":"Bare","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Pittsburgh Pennsylvania USA"}]},{"given":"Bhiksha","family":"Raj","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Pittsburgh Pennsylvania USA"},{"name":"Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates"}]},{"given":"Hyungon","family":"Yoo","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University Pittsburgh Pennsylvania USA"}]}],"member":"311","published-online":{"date-parts":[[2023,8,7]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2978950"},{"key":"e_1_2_10_3_1","unstructured":"Beltagy I. M. E.Peters andA.Cohan.2020. \u201cLongformer: The Long\u2010Document Transformer.\u201darXiv preprint arXiv:2004.05150.https:\/\/arxiv.org\/abs\/2004.05150"},{"key":"e_1_2_10_4_1","doi-asserted-by":"crossref","unstructured":"Bhatt S. S.Joglekar S.Bano andN.Sastry.2018. \u201cIlluminating an Ecosystem of Partisan Websites.\u201d InCompanion Proceedings of The Web Conference 2018 545\u201354.","DOI":"10.1145\/3184558.3188725"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.frl.2022.102781"},{"key":"e_1_2_10_6_1","unstructured":"DeSilver D.2022.The polarization in today's Congress has roots that go back decades. Pew Research Center.https:\/\/www.pewresearch.org\/short\u2010reads\/2022\/03\/10\/the\u2010polarization\u2010in\u2010todays\u2010congress\u2010has\u2010roots\u2010that\u2010go\u2010back\u2010decades\/"},{"key":"e_1_2_10_7_1","unstructured":"Devlin J. M.\u2010W.Chang K.Lee andK.Toutanova.2018. \u201cBert: Pre\u2010Training of Deep Bidirectional Transformers for Language Understanding.\u201darXiv preprint arXiv:1810.04805.https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","unstructured":"Hamilton W. L. J.Leskovec andD.Jurafsky.2016. \u201cDiachronic Word Embeddings Reveal Statistical Laws of Semantic Change.\u201darXiv preprint arXiv:1605.09096.https:\/\/arxiv.org\/abs\/1605.09096","DOI":"10.18653\/v1\/P16-1141"},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","unstructured":"Jiang S. R. E.Robertson andC.Wilson.2020. \u201cReasoning About Political Bias in Content Moderation.\u201d InProceedings of the AAAI Conference on Artificial Intelligence volume34 13669\u201372.","DOI":"10.1609\/aaai.v34i09.7117"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100409"},{"key":"e_1_2_10_11_1","doi-asserted-by":"crossref","unstructured":"KhudaBukhsh A. R. R.Sarkar M. S.Kamlet andT.Mitchell.2021. \u201cWe Don't Speak the Same Language: Interpreting Polarization through Machine Translation.\u201d InProceedings of the AAAI Conference on Artificial Intelligence volume35 14893\u201314901.","DOI":"10.1609\/aaai.v35i17.17748"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","unstructured":"KhudaBukhsh A. R. R.Sarkar M. S.Kamlet andT. M.Mitchell.2022. \u201cFringe News Networks: Dynamics of US News Viewership Following the 2020 Presidential Election.\u201d In14th ACM Web Science Conference 2022 269\u201378.","DOI":"10.1145\/3501247.3531577"},{"key":"e_1_2_10_13_1","unstructured":"Le Q. andT.Mikolov.2014. \u201cDistributed Representations of Sentences and Documents.\u201d InInternational Conference on Machine Learning 1188\u201396. PMLR."},{"key":"e_1_2_10_14_1","unstructured":"Liu Y. M.Ott N.Goyal J.Du M.Joshi D.Chen O.Levy M.Lewis L.Zettlemoyer andV.Stoyanov.2019. \u201cRoberta: A Robustly Optimized Bert Pretraining Approach.\u201darXiv preprint arXiv:1907.11692.https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_2_10_15_1","unstructured":"Mikolov T. K.Chen G.Corrado andJ.Dean.2013. \u201cEfficient Estimation of Word Representations in Vector Space.\u201darXiv preprint arXiv:1301.3781.https:\/\/arxiv.org\/abs\/1301.3781"},{"key":"e_1_2_10_16_1","unstructured":"Palakodety S. A. R.KhudaBukhsh andJ. G.Carbonell.2020. \u201cMining Insights from Large\u2010Scale Corpora Using Fine\u2010Tuned Language Models.\u201d InECAI 2020 1890\u20137. IOS Press."},{"key":"e_1_2_10_17_1","doi-asserted-by":"crossref","unstructured":"Petroni F. T.Rockt\u00e4schel P.Lewis A.Bakhtin Y.Wu A. H.Miller andS.Riedel.2019. \u201cLanguage Models as Knowledge Bases?\u201darXiv preprint arXiv:1909.01066.https:\/\/arxiv.org\/abs\/1909.01066","DOI":"10.18653\/v1\/D19-1250"},{"key":"e_1_2_10_18_1","unstructured":"Pew Research Center.2019.In a Politically Polarized Era Sharp Divides in Both Partisan Coalitions.https:\/\/www.pewresearch.org\/politics\/2019\/12\/17\/in\u2010a\u2010politically\u2010polarized\u2010era\u2010sharp\u2010divides\u2010in\u2010both\u2010partisan\u2010coalitions\/"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.2307\/2131242"},{"key":"e_1_2_10_20_1","doi-asserted-by":"crossref","unstructured":"Rajani N. F. B.McCann C.Xiong andR.Socher.2019. \u201cExplain Yourself! Leveraging Language Models for Commonsense Reasoning.\u201darXiv preprint arXiv:1906.02361.https:\/\/arxiv.org\/abs\/1906.02361","DOI":"10.18653\/v1\/P19-1487"},{"key":"e_1_2_10_21_1","unstructured":"Vaswani A. N.Shazeer N.Parmar J.Uszkoreit L.Jones A. N.Gomez \u0141.Kaiser andI.Polosukhin.2017. \u201cAttention is All You Need.\u201d InAdvances in Neural Information Processing Systems 30."}],"container-title":["AI Magazine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aaai.12104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T18:01:14Z","timestamp":1694714474000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/aaai.12104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":20,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["10.1002\/aaai.12104"],"URL":"http:\/\/dx.doi.org\/10.1002\/aaai.12104","archive":["Portico"],"relation":{},"ISSN":["0738-4602","2371-9621"],"issn-type":[{"value":"0738-4602","type":"print"},{"value":"2371-9621","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"2023-07-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-07-24","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}
