{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:36:22Z","timestamp":1786556182558,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061355","type":"print"},{"value":"9783032061362","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-06136-2_11","type":"book-chapter","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T18:38:16Z","timestamp":1758911896000},"page":"110-123","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Is Word2Vec Dead for\u00a0Topic Modeling? A Case Study on\u00a0Hospitality Opinion Mining"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3812-1341","authenticated-orcid":false,"given":"Marc-Alexis","family":"Aza\u00efs","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4615-1563","authenticated-orcid":false,"given":"Jean-Loup","family":"Guillaume","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-439X","authenticated-orcid":false,"given":"Micka\u00ebl","family":"Coustaty","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"11_CR1","doi-asserted-by":"publisher","unstructured":"Ameur, A., Hamdi, S., Ben\u00a0Yahia, S.: Sentiment analysis for hotel reviews: a systematic literature review. ACM Comput. Surv. 56(2) (2023). https:\/\/doi.org\/10.1145\/3605152","DOI":"10.1145\/3605152"},{"key":"11_CR2","unstructured":"Antognini, D., Faltings, B.: Hotelrec: a novel very large-scale hotel recommendation dataset. In: Proceedings of the 12th Language Resources and Evaluation Conference. pp. 4917\u20134923. European Language Resources Association, Marseille (2020). https:\/\/www.aclweb.org\/anthology\/2020.lrec-1.605"},{"key":"11_CR3","unstructured":"Antoniak, M.: Topic modeling for the people (2022). https:\/\/maria-antoniak.github.io\/2022\/07\/27\/topic-modeling-for-the-people.html. Accessed 02 June 2025"},{"key":"11_CR4","unstructured":"Arefieva, V., Egger, R.: Tourbert: a pretrained language model for the tourism industry. ArXiv arxiv:2201.07449 (2022). https:\/\/api.semanticscholar.org\/CorpusID:246035422"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Balloccu, S., Schmidtov\u00e1, P., Lango, M., Dusek, O.: Leak, cheat, repeat: Data contamination and evaluation malpractices in closed-source LLMs. In: Graham, Y., Purver, M. (eds.) Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, volume 1: Long Papers, pp. 67\u201393. Association for Computational Linguistics, St. Julian\u2019s (2024). https:\/\/aclanthology.org\/2024.eacl-long.5\/","DOI":"10.18653\/v1\/2024.eacl-long.5"},{"key":"11_CR6","unstructured":"Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3(Jan), 993\u20131022 (2003)"},{"key":"11_CR7","unstructured":"Botana, I.L.R., Bol\u00f3n-Canedo, V., Guijarro-Berdi\u00f1as, B., Alonso-Betanzos, A.: Explain and conquer: personalised text-based reviews to achieve transparency (2022). https:\/\/arxiv.org\/abs\/2205.01759"},{"issue":"131","key":"11_CR8","first-page":"1","volume":"20","author":"S Burkhardt","year":"2019","unstructured":"Burkhardt, S., Kramer, S.: Decoupling sparsity and smoothness in the dirichlet variational autoencoder topic model. J. Mach. Learn. Res. 20(131), 1\u201327 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR9","unstructured":"Chang, J., Gerrish, S., Wang, C., Boyd-Graber, J., Blei, D.: Reading tea leaves: how humans interpret topic models. Adv. Neural Inf. Process. Syst. 22 (2009)"},{"key":"11_CR10","doi-asserted-by":"publisher","unstructured":"Chebolu, S.U.S., Dernoncourt, F., Lipka, N., Solorio, T.: A review of datasets for aspect-based sentiment analysis. In: Park, J.C., et al. (eds.) Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 611\u2013628. Association for Computational Linguistics, Nusa Dua (2023). https:\/\/doi.org\/10.18653\/v1\/2023.ijcnlp-main.41. https:\/\/aclanthology.org\/2023.ijcnlp-main.41\/","DOI":"10.18653\/v1\/2023.ijcnlp-main.41"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Chebolu, S.U.S., Dernoncourt, F., Lipka, N., Solorio, T.: OATS: a challenge dataset for opinion aspect target sentiment joint detection for aspect-based sentiment analysis. In: Calzolari, N., Kan, M.Y., Hoste, V., Lenci, A., Sakti, S., Xue, N. (eds.) Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 12336\u201312347. ELRA and ICCL, Torino (2024). https:\/\/aclanthology.org\/2024.lrec-main.1080\/","DOI":"10.63317\/3jphhaf4ivee"},{"key":"11_CR12","doi-asserted-by":"publisher","unstructured":"Choi, A., Akter, S.S., Singh, J., Anastasopoulos, A.: The LLM effect: are humans truly using LLMs, or are they being influenced by them instead? In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 22032\u201322054. Association for Computational Linguistics, Miami (2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.1230. https:\/\/aclanthology.org\/2024.emnlp-main.1230\/","DOI":"10.18653\/v1\/2024.emnlp-main.1230"},{"key":"11_CR13","unstructured":"Doogan, C.: A Topic is not a theme: towards a contextualised approach to topic modelling. Ph.D. thesis, Monash University, Australia (2022)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Doogan, C., Buntine, W.: Topic model or topic twaddle? Re-evaluating demantic interpretability measures. In: North American Association for Computational Linguistics 2021, pp. 3824\u20133848. Association for Computational Linguistics (ACL) (2021)","DOI":"10.18653\/v1\/2021.naacl-main.300"},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Ghafouri, V., Such, J., Suarez-Tangil, G.: I love pineapple on pizza!= I hate pineapple on pizza: Stance-aware sentence transformers for opinion mining. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 21046\u201321058. Association for Computational Linguistics, Miami (2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.1171. https:\/\/aclanthology.org\/2024.emnlp-main.1171\/","DOI":"10.18653\/v1\/2024.emnlp-main.1171"},{"issue":"1","key":"11_CR16","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1146\/annurev-polisci-053119-015921","volume":"24","author":"J Grimmer","year":"2021","unstructured":"Grimmer, J., Roberts, M.E., Stewart, B.M.: Machine learning for social science: an agnostic approach. Annu. Rev. Polit. Sci. 24(1), 395\u2013419 (2021)","journal-title":"Annu. Rev. Polit. Sci."},{"key":"11_CR17","unstructured":"Grimmer, J., Roberts, M.E., Stewart, B.M.: Text as Data: A New Framework for Machine Learning and the Social Sciences. Princeton University Press, Princeton (2022)"},{"issue":"3","key":"11_CR18","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1093\/pan\/mps028","volume":"21","author":"J Grimmer","year":"2013","unstructured":"Grimmer, J., Stewart, B.M.: Text as data: the promise and pitfalls of automatic content analysis methods for political texts. Polit. Anal. 21(3), 267\u2013297 (2013)","journal-title":"Polit. Anal."},{"key":"11_CR19","unstructured":"Grootendorst, M.: Bertopic: neural topic modeling with a class-based tf-idf procedure (2022). https:\/\/arxiv.org\/abs\/2203.05794"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Harrando, I., Lisena, P., Troncy, R.: Apples to apples: a systematic evaluation of topic models. In: Mitkov, R., Angelova, G. (eds.) Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pp. 483\u2013493. INCOMA Ltd., Held Online (2021). https:\/\/aclanthology.org\/2021.ranlp-1.55\/","DOI":"10.26615\/978-954-452-072-4_055"},{"key":"11_CR21","doi-asserted-by":"publisher","unstructured":"He, R., Lee, W.S., Ng, H.T., Dahlmeier, D.: An unsupervised neural attention model for aspect extraction. In: Barzilay, R., Kan, M.Y. (eds.) Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 388\u2013397. Association for Computational Linguistics, Vancouver (2017). https:\/\/doi.org\/10.18653\/v1\/P17-1036. https:\/\/aclanthology.org\/P17-1036\/","DOI":"10.18653\/v1\/P17-1036"},{"key":"11_CR22","first-page":"2018","volume":"34","author":"A Hoyle","year":"2021","unstructured":"Hoyle, A., Goel, P., Hian-Cheong, A., Peskov, D., Boyd-Graber, J., Resnik, P.: Is automated topic model evaluation broken? The incoherence of coherence. Adv. Neural. Inf. Process. Syst. 34, 2018\u20132033 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR23","doi-asserted-by":"publisher","unstructured":"Hoyle, A.M., Goel, P., Resnik, P.: Improving neural topic models using knowledge distillation. In: Webber, B., Cohn, T., He, Y., Liu, Y. (eds.) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1752\u20131771. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.137. https:\/\/aclanthology.org\/2020.emnlp-main.137\/","DOI":"10.18653\/v1\/2020.emnlp-main.137"},{"key":"11_CR24","doi-asserted-by":"publisher","unstructured":"Hoyle, A.M., Sarkar, R., Goel, P., Resnik, P.: Are neural topic models broken? In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2022, pp. 5321\u20135344. Association for Computational Linguistics, Abu Dhabi (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-emnlp.390. https:\/\/aclanthology.org\/2022.findings-emnlp.390\/","DOI":"10.18653\/v1\/2022.findings-emnlp.390"},{"key":"11_CR25","doi-asserted-by":"publisher","unstructured":"Kamoen, N., Mos, M.B., Dekker (Robbin), W.F.: A hotel that is not bad isn\u2019t good. the effects of valence framing and expectation in online reviews on text, reviewer and product appreciation. J. Pragmat. 75, 28\u201343 (2015). https:\/\/doi.org\/10.1016\/j.pragma.2014.10.007. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0378216614002112","DOI":"10.1016\/j.pragma.2014.10.007"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Kim, J., Na, Y., Kim, K., Lee, S.R., Chae, D.K.: SentiCSE: a sentiment-aware contrastive sentence embedding framework with sentiment-guided textual similarity. In: Calzolari, N., Kan, M.Y., Hoste, V., Lenci, A., Sakti, S., Xue, N. (eds.) Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 14693\u201314704. ELRA and ICCL, Torino (2024). https:\/\/aclanthology.org\/2024.lrec-main.1280\/","DOI":"10.63317\/3f6dvup92749"},{"key":"11_CR27","doi-asserted-by":"publisher","unstructured":"Laureate, C.D., Poet, W.B., Linger, H.: A systematic review of the use of topic models for short text social media analysis. Artif. Intell. Rev. 56(12), 14223\u201314255 (2023). https:\/\/doi.org\/10.1007\/s10462-023-10471-x","DOI":"10.1007\/s10462-023-10471-x"},{"key":"11_CR28","unstructured":"Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., Zhang, M.: Towards general text embeddings with multi-stage contrastive learning (2023). https:\/\/arxiv.org\/abs\/2308.03281"},{"key":"11_CR29","unstructured":"Li, Z., et al.: Large language models struggle to describe the haystack without human help: human-in-the-loop evaluation of llms (2025). https:\/\/arxiv.org\/abs\/2502.14748"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Improving the TENOR of labeling: Re-evaluating topic models for content analysis. In: Graham, Y., Purver, M. (eds.) Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 840\u2013859. Association for Computational Linguistics, St. Julian\u2019s (2024). https:\/\/aclanthology.org\/2024.eacl-long.51\/","DOI":"10.18653\/v1\/2024.eacl-long.51"},{"key":"11_CR31","unstructured":"Liu, B.: Sentiment Analysis and Opinion Mining. Springer, Cham (2022)"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Marjanen, J., Zosa, E., Hengchen, S., Pivovarova, L., Tolonen, M.: Topic modelling discourse dynamics in historical newspapers. arXiv preprint arXiv:2011.10428 (2020)","DOI":"10.5617\/dhnbpub.11235"},{"key":"11_CR33","unstructured":"McCallum, A.K.: Mallet: a machine learning for languagetoolkit (2002). http:\/\/mallet.cs.umass.edu"},{"key":"11_CR34","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space (2013). https:\/\/arxiv.org\/abs\/1301.3781"},{"key":"11_CR35","doi-asserted-by":"publisher","unstructured":"Mitcheltree, C., Wharton, S., Saluja, A.: Using aspect extraction approaches to generate review summaries and user profiles. In: Bangalore, S., Chu-Carroll, J., Li, Y. (eds.) Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 3 (Industry Papers), pp. 68\u201375. Association for Computational Linguistics, New Orleans - Louisiana (2018). https:\/\/doi.org\/10.18653\/v1\/N18-3009. https:\/\/aclanthology.org\/N18-3009\/","DOI":"10.18653\/v1\/N18-3009"},{"key":"11_CR36","doi-asserted-by":"publisher","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: massive text embedding benchmark. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2014\u20132037. Association for Computational Linguistics, Dubrovnik (2023). https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.148. https:\/\/aclanthology.org\/2023.eacl-main.148\/","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"11_CR37","doi-asserted-by":"publisher","unstructured":"Nguyen, T.N., Ngo, H., Nguyen, K.H., Cao, T.D.: A self-enhancement multitask framework for unsupervised aspect category detection. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 8043\u20138054. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.500. https:\/\/aclanthology.org\/2023.emnlp-main.500\/","DOI":"10.18653\/v1\/2023.emnlp-main.500"},{"key":"11_CR38","unstructured":"Ni, J., et al.: Large dual encoders are generalizable retrievers (2021). https:\/\/arxiv.org\/abs\/2112.07899"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Ni, J., et al.: Sentence-t5: scalable sentence encoders from pre-trained text-to-text models (2021). https:\/\/arxiv.org\/abs\/2108.08877","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"11_CR40","doi-asserted-by":"publisher","unstructured":"Nikolaev, D., Pad\u00f3, S.: Representation biases in sentence transformers. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 3701\u20133716. Association for Computational Linguistics, Dubrovnik (2023). https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.268. https:\/\/aclanthology.org\/2023.eacl-main.268\/","DOI":"10.18653\/v1\/2023.eacl-main.268"},{"key":"11_CR41","doi-asserted-by":"publisher","unstructured":"Pham, C.M., Hoyle, A., Sun, S., Resnik, P., Iyyer, M.: TopicGPT: a prompt-based topic modeling framework. In: Duh, K., Gomez, H., Bethard, S. (eds.) Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1: Long Papers, pp. 2956\u20132984. Association for Computational Linguistics, Mexico City (2024). https:\/\/doi.org\/10.18653\/v1\/2024.naacl-long.164. https:\/\/aclanthology.org\/2024.naacl-long.164\/","DOI":"10.18653\/v1\/2024.naacl-long.164"},{"key":"11_CR42","doi-asserted-by":"publisher","unstructured":"Pontiki, M., et al.: SemEval-2016 task 5: aspect based sentiment analysis. In: Bethard, S., Carpuat, M., Cer, D., Jurgens, D., Nakov, P., Zesch, T. (eds.) Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), pp. 19\u201330. Association for Computational Linguistics, San Diego (2016). https:\/\/doi.org\/10.18653\/v1\/S16-1002. https:\/\/aclanthology.org\/S16-1002\/","DOI":"10.18653\/v1\/S16-1002"},{"key":"11_CR43","doi-asserted-by":"crossref","unstructured":"Pontiki, M., Galanis, D., Papageorgiou, H., Manandhar, S., Androutsopoulos, I.: Semeval-2015 task 12: aspect based sentiment analysis. In: International Workshop on Semantic Evaluation (2015). https:\/\/api.semanticscholar.org\/CorpusID:61874237","DOI":"10.18653\/v1\/S15-2082"},{"key":"11_CR44","doi-asserted-by":"publisher","unstructured":"Pontiki, M., Galanis, D., Pavlopoulos, J., Papageorgiou, H., Androutsopoulos, I., Manandhar, S.: SemEval-2014 task 4: aspect based sentiment analysis. In: Nakov, P., Zesch, T. (eds.) Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014), pp. 27\u201335. Association for Computational Linguistics, Dublin (2014). https:\/\/doi.org\/10.3115\/v1\/S14-2004. https:\/\/aclanthology.org\/S14-2004\/","DOI":"10.3115\/v1\/S14-2004"},{"issue":"3","key":"11_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.jik.2024.100517","volume":"9","author":"R Raman","year":"2024","unstructured":"Raman, R., Pattnaik, D., Hughes, L., Nedungadi, P.: Unveiling the dynamics of ai applications: a review of reviews using scientometrics and bertopic modeling. J. Innov. Knowl. 9(3), 100517 (2024)","journal-title":"J. Innov. Knowl."},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Reif, E., Qian, C., Wexler, J., Kahng, M.: Automatic histograms: leveraging language models for text dataset exploration. In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp.\u00a01\u20139 (2024)","DOI":"10.1145\/3613905.3650798"},{"key":"11_CR47","unstructured":"Reimers, N.: Train the best sentence embedding model ever with 1b training pairs (2021). https:\/\/discuss.huggingface.co\/t\/train-the-best-sentence-embedding-model-ever-with-1b-training-pairs\/7354. hugging Face Forums"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. In: Conference on Empirical Methods in Natural Language Processing (2019). https:\/\/api.semanticscholar.org\/CorpusID:201646309","DOI":"10.18653\/v1\/D19-1410"},{"key":"11_CR49","unstructured":"Rogers, A., Luccioni, A.S.: Position: key claims in llm research have a long tail of footnotes. arXiv preprint arXiv:2308.07120 (2023)"},{"key":"11_CR50","doi-asserted-by":"publisher","unstructured":"R\u00f6ttger, P., Vidgen, B., Hovy, D., Pierrehumbert, J.: Two contrasting data annotation paradigms for subjective NLP tasks. In: Carpuat, M., de\u00a0Marneffe, M.C., Meza\u00a0Ruiz, I.V. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 175\u2013190. Association for Computational Linguistics, Seattle (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.13. https:\/\/aclanthology.org\/2022.naacl-main.13\/","DOI":"10.18653\/v1\/2022.naacl-main.13"},{"key":"11_CR51","unstructured":"Saxon, M., Holtzman, A., West, P., Wang, W.Y., Saphra, N.: Benchmarks as microscopes: a call for model metrology. arXiv preprint arXiv:2407.16711 (2024)"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Schofield, A., Wu, S., Bayard\u00a0de Volo, T., Kuze, T., Gomez, A., Sultana, S.: \u201cmy very subjective human interpretation\u201d: domain expert perspectives on navigating the text analysis loop for topic models. In: Proceedings of the ACM on Human-Computer Interaction, vol. 9, no. 1, pp. 1\u201330 (2025)","DOI":"10.1145\/3701201"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Shadrova, A.: Topic models do not model topics: epistemological remarks and steps towards best practices. J. Data Min. Dig. Human. 2021 (2021)","DOI":"10.46298\/jdmdh.7595"},{"key":"11_CR54","unstructured":"Singh, S., et\u00a0al.: The leaderboard illusion. arXiv preprint arXiv:2504.20879 (2025)"},{"key":"11_CR55","doi-asserted-by":"publisher","unstructured":"Tedeschi, S., et al.: What\u2019s the meaning of superhuman performance in today\u2019s NLU? In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 12471\u201312491. Association for Computational Linguistics, Toronto (2023). \u00a0https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.697. https:\/\/aclanthology.org\/2023.acl-long.697\/","DOI":"10.18653\/v1\/2023.acl-long.697"},{"key":"11_CR56","doi-asserted-by":"publisher","unstructured":"Tulkens, S., van Cranenburgh, A.: Embarrassingly simple unsupervised aspect extraction. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3182\u20133187. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.290. https:\/\/aclanthology.org\/2020.acl-main.290\/","DOI":"10.18653\/v1\/2020.acl-main.290"},{"key":"11_CR57","unstructured":"Tulkens, S., van Dongen, T.: Model2vec: fast state-of-the-art static embeddings (2024). https:\/\/github.com\/MinishLab\/model2vec"},{"key":"11_CR58","doi-asserted-by":"publisher","unstructured":"Venkit, P., et al.: The sentiment problem: a critical survey towards deconstructing sentiment analysis. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 13743\u201313763. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.848. https:\/\/aclanthology.org\/2023.emnlp-main.848\/","DOI":"10.18653\/v1\/2023.emnlp-main.848"},{"key":"11_CR59","doi-asserted-by":"publisher","unstructured":"Wang, F., et al.: Text2Topic: multi-label text classification system for efficient topic detection in user generated content with zero-shot capabilities. In: Wang, M., Zitouni, I. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pp. 93\u2013103. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-industry.10. https:\/\/aclanthology.org\/2023.emnlp-industry.10\/","DOI":"10.18653\/v1\/2023.emnlp-industry.10"},{"key":"11_CR60","unstructured":"Wang, L., et al.: Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)"},{"key":"11_CR61","unstructured":"Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., Wei, F.: Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368 (2023)"}],"container-title":["Communications in Computer and Information Science","New Trends in Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06136-2_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T16:48:35Z","timestamp":1786553315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06136-2_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"ISBN":["9783032061355","9783032061362"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06136-2_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"27 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tampere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2025.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}