{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T16:19:57Z","timestamp":1764260397660,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031790348"},{"type":"electronic","value":"9783031790355"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-79035-5_24","type":"book-chapter","created":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T22:09:18Z","timestamp":1738188558000},"page":"346-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Investigating Methods to\u00a0Detect Off-Topic Essays"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9696-6231","authenticated-orcid":false,"given":"Joyce M.","family":"Silva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4209-9013","authenticated-orcid":false,"given":"Rafael T.","family":"Anchi\u00eata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4589-6157","authenticated-orcid":false,"given":"Rog\u00e9rio F.","family":"de Sousa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1558-3830","authenticated-orcid":false,"given":"Raimundo S.","family":"Moura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,30]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Amorim, E., Veloso, A.: A multi-aspect analysis of automatic essay scoring for Brazilian Portuguese. In: Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics, pp. 94\u2013102. Association for Computational Linguistics, Valencia, Spain (2017)","DOI":"10.18653\/v1\/E17-4010"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Beigman\u00a0Klebanov, B., Flor, M., Gyawali, B.: Topicality-based indices for essay scoring. In: Proceedings of the 11th Workshop on Innovative Use of NLP for Building Educational Applications, pp. 63\u201372. Association for Computational Linguistics, San Diego, CA (2016)","DOI":"10.18653\/v1\/W16-0507"},{"key":"24_CR3","unstructured":"Bird, S., Klein, E., Loper, E.: Natural language processing with Python: analyzing text with the natural language toolkit. O\u2019Reilly Media, Inc. (2009)"},{"key":"24_CR4","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993\u20131022 (2003)"},{"key":"24_CR5","unstructured":"Caseli, H.M., Nunes, M.G.V. (eds.): Processamento de Linguagem Natural: Conceitos, T\u00e9cnicas e Aplica\u00e7\u00f5es em Portugu\u00eas. BPLN, 2 edn. (2024). ISBN 978-65-00-95750-1"},{"key":"24_CR6","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"key":"24_CR7","unstructured":"Das, S.D., Vadi, Y.A., Yadav, K.: Transformer-based joint modelling for automatic essay scoring and off-topic detection. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 16751\u201316761. ELRA and ICCL, Torino, Italia (2024)"},{"key":"24_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019)"},{"key":"24_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/978-3-319-99722-3_18","volume-title":"Computational Processing of the Portuguese Language","author":"E Fonseca","year":"2018","unstructured":"Fonseca, E., Medeiros, I., Kamikawachi, D., Bokan, A.: Automatically grading Brazilian student essays. In: Villavicencio, A., et al. (eds.) PROPOR 2018. LNCS (LNAI), vol. 11122, pp. 170\u2013179. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99722-3_18"},{"key":"24_CR10","unstructured":"Hartmann, N., Fonseca, E., Shulby, C., Treviso, M., Silva, J., Alu\u00edsio, S.: Portuguese word embeddings: evaluating on word analogies and natural language tasks. In: Proceedings of the 11th Brazilian Symposium in Information and Human Language Technology, pp. 122\u2013131. Sociedade Brasileira de Computa\u00e7\u00e3o, Uberl\u00e2ndia, Brazil (2017)"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"He, H., Bai, Y., Garcia, E.A., Li, S.: Adasyn: adaptive synthetic sampling approach for imbalanced learning. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp. 1322\u20131328. IEEE, Hong Kong (2008)","DOI":"10.1109\/IJCNN.2008.4633969"},{"issue":"2","key":"24_CR12","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1017\/S1351324906004189","volume":"12","author":"D Higgins","year":"2006","unstructured":"Higgins, D., Burstein, J., Attali, Y.: Identifying off-topic student essays without topic-specific training data. Nat. Lang. Eng. 12(2), 145\u2013159 (2006)","journal-title":"Nat. Lang. Eng."},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Huang, P., Li, L., Wu, C., Zhang, X., Liu, Z.: A study of sentence-bert based essay off-topic detection. In: Proceedings of the 4th International Conference on Computing, Networks and Internet of Things, pp. 515\u2013519. Association for Computing Machinery, Xiamen, China (2023)","DOI":"10.1145\/3603781.3603871"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Kabra, A., Bhatia, M., Singla, Y.K., Jessy\u00a0Li, J., Ratn\u00a0Shah, R.: Evaluation toolkit for robustness testing of automatic essay scoring systems. In: Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD), pp. 90\u201399. Association for Computing Machinery, Bangalore, India (2022)","DOI":"10.1145\/3493700.3493765"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Ke, Z., Ng, V.: Automated essay scoring: a survey of the state of the art. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 6300\u20136308. AAAI Press, Macao, China (2019)","DOI":"10.24963\/ijcai.2019\/879"},{"key":"24_CR16","unstructured":"Kusner, M., Sun, Y., Kolkin, N., Weinberger, K.: From word embeddings to document distances. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 957\u2013966. Proceedings of Machine Learning Research, PMLR, Lille, France (2015)"},{"issue":"2\u20133","key":"24_CR17","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1080\/01638539809545028","volume":"25","author":"TK Landauer","year":"1998","unstructured":"Landauer, T.K., Foltz, P.W., Laham, D.: An introduction to latent semantic analysis. Discourse Process. 25(2\u20133), 259\u2013284 (1998)","journal-title":"Discourse Process."},{"issue":"17","key":"24_CR18","first-page":"1","volume":"18","author":"G Lema\u00eetre","year":"2017","unstructured":"Lema\u00eetre, G., Nogueira, F., Aridas, C.K.: Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. J. Mach. Learn. Res. 18(17), 1\u20135 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Marinho, J.C., Anchi\u00eata, R.T., Moura, R.S.: Essay-BR: a Brazilian corpus of essays. In: XXXIV Simp\u00f3sio Brasileiro de Banco de Dados: Dataset Showcase Workshop. SBBD 2021, pp. 53\u201364. SBC, Online (2021)","DOI":"10.5753\/dsw.2021.17414"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Marinho, J.C., C., F., Anchi\u00eata, R.T., Moura, R.S.: Automated essay scoring: an approach based on enem competencies. In: Anais do XIX Encontro Nacional de Intelig\u00eancia Artificial e Computacional, pp. 49\u201360. SBC, Campinas, Brazil (2022)","DOI":"10.5753\/eniac.2022.227202"},{"key":"24_CR21","unstructured":"Page, E.B.: The imminence of... grading essays by computer. The Phi Delta Kappan 47(5), 238\u2013243 (1966)"},{"issue":"03","key":"24_CR22","doi-asserted-by":"publisher","first-page":"177","DOI":"10.5753\/rbie.2019.27.03.177","volume":"27","author":"G Passero","year":"2019","unstructured":"Passero, G., Ferreira, R., Dazzi, R.L.S.: Off-topic essay detection: a comparative study on the Portuguese language. Revista Brasileira de Inform\u00e1tica na Educa\u00e7\u00e3o 27(03), 177\u2013190 (2019)","journal-title":"Revista Brasileira de Inform\u00e1tica na Educa\u00e7\u00e3o"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Passero, G., Ferreira, R., Haendchen\u00a0Filho, A., Dazzi, R.: Off-topic essay detection: a systematic review. In: Proceedings of the XXVIII Brazilian Symposium on Computers in Education, pp. 51\u201360. SBC, Recife, Brazil (2017)","DOI":"10.5753\/cbie.sbie.2017.51"},{"key":"24_CR24","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Pinho, C.M.D.A., Gaspar, M.A., Sassi, R.J.: Aplica\u00e7\u00e3o de t\u00e9cnicas de intelig\u00eancia artificial para classifica\u00e7\u00e3o de fuga ao tema em reda\u00e7\u00f5es. Educa\u00e7\u00e3o em Revista 40, e39773 (2024)","DOI":"10.1590\/0102-469839773"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. 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), pp. 3982\u20133992. Association for Computational Linguistics, Hong Kong, China (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"24_CR27","unstructured":"Shermis, M.D., Barrera, F.D.: Exit assessments: evaluating writing ability through automated essay scoring. In: Annual Meeting of the American Educational Research Association, pp. 1\u201330. ERIC, New Orleans, LA (2002)"},{"key":"24_CR28","unstructured":"de\u00a0Sousa, R.F., Marinho, J.C., Neto, F.A.R., Anchi\u00eata, R.T., Moura, R.S.: PiLN at PROPOR: a BERT-based strategy for grading narrative essays. In: Proceedings of the 16th International Conference on Computational Processing of Portuguese - Vol. 2, pp. 10\u201313. Association for Computational Linguistics, Santiago de Compostela, Galicia\/Spain (2024)"},{"key":"24_CR29","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/978-3-030-61377-8_28","volume-title":"Intelligent Systems","author":"F Souza","year":"2020","unstructured":"Souza, F., Nogueira, R., Lotufo, R.: BERTimbau: pretrained BERT models for Brazilian Portuguese. In: Cerri, R., Prati, R.C. (eds.) BRACIS 2020. LNCS (LNAI), vol. 12319, pp. 403\u2013417. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-61377-8_28"},{"key":"24_CR30","unstructured":"\u0158eh\u016f\u0159ek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: Proceedings of LREC 2010 workshop New Challenges for NLP Frameworks, pp. 46\u201350. University of Malta, Valletta, Malta (2010)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-79035-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T22:09:29Z","timestamp":1738188569000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-79035-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031790348","9783031790355"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-79035-5_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"30 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bel\u00e9m do Par\u00e1","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}