{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:37Z","timestamp":1750309537044,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,13]]},"DOI":"10.1145\/3711542.3711568","type":"proceedings-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T04:46:56Z","timestamp":1744606016000},"page":"179-185","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dialogue-Level Data Augmentation for Conversation Derailment Forecasting and Topic-Shift Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6148-8439","authenticated-orcid":false,"given":"Nerses","family":"Yuzbashyan","sequence":"first","affiliation":[{"name":"Department of Linguistics, University of Antwerp, Antwerpen, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9517-5791","authenticated-orcid":false,"given":"Nikolay","family":"Banar","sequence":"additional","affiliation":[{"name":"Department of Linguistics, University of Antwerp, Antwerpen, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9832-7890","authenticated-orcid":false,"given":"Walter","family":"Daelemans","sequence":"additional","affiliation":[{"name":"Department of Linguistics, University of Antwerp, Antwerpen, Belgium"}]}],"member":"320","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Laith Alzubaidi Jinshuai Bai Aiman Al-Sabaawi Jose Santamar\u00eda Ahmed\u00a0Shihab Albahri Bashar Sami\u00a0Nayyef Al-dabbagh Mohammed\u00a0A Fadhel Mohamed Manoufali Jinglan Zhang Ali\u00a0H Al-Timemy et\u00a0al. 2023. A survey on deep learning tools dealing with data scarcity: definitions challenges solutions tips and applications. Journal of Big Data 10 1 (2023) 46.","DOI":"10.1186\/s40537-023-00727-2"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.155"},{"key":"e_1_3_3_1_4_2","unstructured":"Somnath Banerjee Maulindu Sarkar Nancy Agrawal Punyajoy Saha and Mithun Das. 2021. Exploring transformer based models to identify hate speech and offensive content in english and indo-aryan languages. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.13974 (2021). https:\/\/arxiv.org\/pdf\/2111.13974.pdf"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Markus Bayer Marc-Andr\u00e9 Kaufhold and Christian Reuter. 2022. A survey on data augmentation for text classification. Comput. Surveys 55 7 (2022) 1\u201339.","DOI":"10.1145\/3544558"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Pete Burnap and Matthew\u00a0L Williams. 2015. Cyber hate speech on twitter: An application of machine classification and statistical modeling for policy and decision making. Policy & internet 7 2 (2015) 223\u2013242. 10.1002\/poi3.85","DOI":"10.1002\/poi3.85"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1481"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.63"},{"key":"e_1_3_3_1_9_2","volume-title":"NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research","author":"Chen Maximillian","year":"2022","unstructured":"Maximillian Chen, Alexandros Papangelis, Chenyang Tao, Andy Rosenbaum, Seokhwan Kim, Yang Liu, Zhou Yu, and Dilek Hakkani-Tur. 2022. Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding. In NeurIPS 2022 Workshop on Synthetic Data for Empowering ML Research."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.343"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v11i1.14955"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Bosheng Ding Chengwei Qin Ruochen Zhao Tianze Luo Xinze Li Guizhen Chen Wenhan Xia Junjie Hu Anh\u00a0Tuan Luu and Shafiq Joty. 2024. Data augmentation using llms: Data perspectives learning paradigms and challenges. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.02990 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.97"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Sufeng Duan Hai Zhao and Dongdong Zhang. 2023. Syntax-aware data augmentation for neural machine translation. IEEE\/ACM Transactions on Audio Speech and Language Processing (2023).","DOI":"10.1109\/TASLP.2023.3301214"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.deelio-1.4"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.84"},{"key":"e_1_3_3_1_16_2","unstructured":"Pieter Fivez Walter Daelemans Tim Van\u00a0de Cruys Yury Kashnitsky Savvas Chamezopoulos Hadi Mohammadi Anastasia Giachanou Ayoub Bagheri Wessel Poelman Juraj Vladika et\u00a0al. 2024. The CLIN33 Shared Task on the Detection of Text Generated by Large Language Models. Computational Linguistics in the Netherlands Journal 13 (2024) 233\u2013259."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Alon Halevy Cristian Canton-Ferrer Hao Ma Umut Ozertem Patrick Pantel Marzieh Saeidi Fabrizio Silvestri and Ves Stoyanov. 2022. Preserving integrity in online social networks. Commun. ACM 65 2 (2022) 92\u201398. 10.1145\/3462671","DOI":"10.1145\/3462671"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.201"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2703"},{"key":"e_1_3_3_1_20_2","first-page":"3658","volume-title":"57th Annual Meeting of the Association for Computational Linguistics, ACL 2019","author":"Jurgens David","year":"2020","unstructured":"David Jurgens, Eshwar Chandrasekharan, and Libby Hemphill. 2020. A just and comprehensive strategy for using NlP to address online abuse. In 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019. Association for Computational Linguistics (ACL), 3658\u20133666."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1357"},{"key":"e_1_3_3_1_22_2","unstructured":"Chiu Ke-Li Collins Annie and Alexander Rohan. 2021. Detecting hate speech with gpt-3. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2103.12407 (2021). https:\/\/arxiv.org\/pdf\/2103.12407.pdf"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1363"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Guangmin Li Hui Wang Yi Ding Kangan Zhou and Xiaowei Yan. 2023. Data augmentation for aspect-based sentiment analysis. International Journal of Machine Learning and Cybernetics 14 1 (2023) 125\u2013133.","DOI":"10.1007\/s13042-022-01535-5"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v12i1.15022"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Xiner Liu Jianshu He Mingzhe Liu Zhengtong Yin Lirong Yin and Wenfeng Zheng. 2023. A scenario-generic neural machine translation data augmentation method. Electronics 12 10 (2023) 2320.","DOI":"10.3390\/electronics12102320"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08473-7_1"},{"key":"e_1_3_3_1_28_2","unstructured":"Yu Meng Jiaxin Huang Yu Zhang and Jiawei Han. 2022. Generating training data with language models: Towards zero-shot language understanding. Advances in Neural Information Processing Systems 35 (2022) 462\u2013477."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.212"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ELEXCOM58812.2023.10370502"},{"key":"e_1_3_3_1_31_2","unstructured":"R OpenAI. 2023. Gpt-4 technical report. arxiv 2303.08774. View in Article 2 5 (2023)."},{"key":"e_1_3_3_1_32_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et\u00a0al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1545"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nlp4convai-1.5"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC54503.2022.9720792"},{"key":"e_1_3_3_1_36_2","first-page":"2178","volume-title":"CLEF (Working Notes)","author":"Uzan Moshe","year":"2021","unstructured":"Moshe Uzan and Yaakov HaCohen-Kerner. 2021. Detecting Hate Speech Spreaders on Twitter using LSTM and BERT in English and Spanish.. In CLEF (Working Notes). 2178\u20132185. https:\/\/ceur-ws.org\/Vol-2936\/paper-194.pdf"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1102"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-2013"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1670"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.145"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Wenjie Yin and Arkaitz Zubiaga. 2021. Towards generalisable hate speech detection: a review on obstacles and solutions. PeerJ Computer Science 7 (2021) e598.","DOI":"10.7717\/peerj-cs.598"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1125"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1205"}],"event":{"name":"NLPIR 2024: 2024 8th International Conference on Natural Language Processing and Information Retrieval","acronym":"NLPIR 2024","location":"Okayama Japan"},"container-title":["Proceedings of the 2024 8th International Conference on Natural Language Processing and Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711542.3711568","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711542.3711568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:29Z","timestamp":1750295909000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711542.3711568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":42,"alternative-id":["10.1145\/3711542.3711568","10.1145\/3711542"],"URL":"https:\/\/doi.org\/10.1145\/3711542.3711568","relation":{},"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"2025-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}