{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:40:04Z","timestamp":1750189204894,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T00:00:00Z","timestamp":1677456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1934925, 1934494"],"award-info":[{"award-number":["1934925, 1934494"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,2,27]]},"DOI":"10.1145\/3539597.3570462","type":"proceedings-article","created":{"date-parts":[[2023,2,22]],"date-time":"2023-02-22T23:27:00Z","timestamp":1677108420000},"page":"868-876","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Combining vs. Transferring Knowledge: Investigating Strategies for Improving Demographic Inference in Low Resource Settings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1926-444X","authenticated-orcid":false,"given":"Yaguang","family":"Liu","sequence":"first","affiliation":[{"name":"Georgetown University, Washington, DC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8300-2970","authenticated-orcid":false,"given":"Lisa","family":"Singh","sequence":"additional","affiliation":[{"name":"Georgetown University, Washington, DC, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,2,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"A. Achille M. Lam R. Tewari A. Ravichandran S. Maji C. C Fowlkes S. Soatto and P. Perona. 2019. Task2vec: Task embedding for meta-learning. In ICCV.","DOI":"10.1109\/ICCV.2019.00653"},{"key":"e_1_3_2_2_2_1","unstructured":"D. Alvarez-Melis and N. Fusi. 2020. Geometric dataset distances via optimal transport. NIPS."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"S. Banerjee C. Akkaya F. Perez-Sorrosal and K. Tsioutsiouliklis. 2019. Hierarchical transfer learning for multi-label text classification. In ACL.","DOI":"10.18653\/v1\/P19-1633"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"C. Budak S. Soroka L. Singh M. Bailey L. Bode N. Chawla P. Davis-Kean M. De Choudhury R. De Veaux U. Hahn et al. 2021. Modeling Considerations for Quantitative Social Science Research Using Social Media Data. (2021).","DOI":"10.31234\/osf.io\/3e2ux"},{"key":"e_1_3_2_2_5_1","unstructured":"X. Chen Y. Wang E. Agichtein and F. Wang. 2015. A comparative study of demographic attribute inference in twitter. In ICWSM."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"K. Cho B. Van Merri\u00ebnboer D. Bahdanau and Y. Bengio. 2014. On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014).","DOI":"10.3115\/v1\/W14-4012"},{"key":"e_1_3_2_2_7_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin J.","year":"2018","unstructured":"J. Devlin, M. Chang, K. Lee, and K. Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_8_1","unstructured":"A. Dosovitskiy L. Beyer A. Kolesnikov D. Weissenborn X. Zhai T. Unterthiner M. Dehghani M. Minderer G. Heigold S. Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_9_1","volume":"201","author":"Kingma D.","unstructured":"D. Kingma and J. Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).","journal-title":"J. Ba."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"A. Klein A. Magge and G. Gonzalez-Hernandez. 2022. ReportAGE: Automatically extracting the exact age of Twitter users based on self-reports in tweets. PloS one (2022).","DOI":"10.1371\/journal.pone.0262087"},{"key":"e_1_3_2_2_11_1","volume-title":"Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning. Journal of Machine Learning Research","author":"Lema\u00ee G.","year":"2017","unstructured":"G. Lema\u00ee, F. Nogueira, and C. Aridas. 2017. Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning. Journal of Machine Learning Research (2017)."},{"key":"e_1_3_2_2_12_1","volume-title":"A conception of adult development. American psychologist","author":"Levinson D.","year":"1986","unstructured":"D. Levinson. 1986. A conception of adult development. American psychologist (1986)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Y. Liu and L. Singh. 2021. Age Inference Using A Hierarchical Attention Neural Network. In CIKM.","DOI":"10.1145\/3459637.3482055"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Y. Liu L. Singh and Z. Mneimneh. 2021. A Comparative Analysis of Classic and Deep Learning Models for Inferring Gender and Age of Twitter Users. In DeLTA.","DOI":"10.5220\/0010559500480058"},{"key":"e_1_3_2_2_15_1","unstructured":"M. Marelli S. Menini M. Baroni L. Bentivogli R. Bernardi and R. Zamparelli. 2014. A SICK cure for the evaluation of compositional distributional semantic models. In LREC."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Y. Miura M. Taniguchi T. Taniguchi and T. Ohkuma. 2017. Unifying text metadata and user network representations with a neural network for geolocation prediction. In ACL.","DOI":"10.18653\/v1\/P17-1116"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Z. Mneimneh J. Pasek L. Singh R. Best L. Bode E. Bruch C. Budak P. Davis-Kean K. Donato N. Ellison et al. 2021. Data Acquisition Sampling and Data Preparation Considerations for Quantitative Social Science Research Using Social Media Data. (2021).","DOI":"10.31234\/osf.io\/k6vyj"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"L. Mou Z. Meng R. Yan G. Li Y. Xu L. Zhang and Z. Jin. 2016. How transferable are neural networks in nlp applications? arXiv preprint arXiv:1603.06111 (2016).","DOI":"10.18653\/v1\/D16-1046"},{"key":"e_1_3_2_2_19_1","unstructured":"A. Ng. 2004. Feature selection L1 vs. L2 regularization and rotational invariance. In ICML."},{"key":"e_1_3_2_2_20_1","volume-title":"and Meder","author":"Nguyen D.","year":"2013","unstructured":"D. Nguyen, R. Gravel, and T. Trieschnigg, D.and Meder. 2013. \u201c How old do you think I am?\" A study of language and age in Twitter. In ICWSM."},{"key":"e_1_3_2_2_21_1","unstructured":"A. Radford J. Kim C. Hallacy A. Ramesh G. Goh S. Agarwal G. Sastry A. Askell P. Mishkin J. Clark et al. 2021. Learning transferable visual models from natural language supervision. arXiv preprint arXiv:2103.00020 (2021)."},{"key":"e_1_3_2_2_22_1","unstructured":"A. Radford K. Narasimhan T. Salimans and I. Sutskever. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_2_23_1","volume-title":"NIPS MLSN Workshop.","author":"Rao D.","year":"2010","unstructured":"D. Rao, D. Yarowsky, et al. 2010. Detecting latent user properties in social media. In NIPS MLSN Workshop."},{"volume-title":"Workshop on Vision and Language.","author":"Sakaki S.","key":"e_1_3_2_2_24_1","unstructured":"S. Sakaki, Y. Miura, X. Ma, K. Hattori, and T. Ohkuma. 2014. Twitter user gender inference using combined analysis of text and image processing. In Workshop on Vision and Language."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"T. Semwal P. Yenigalla G. Mathur and S. Nair. 2018. A practitioners' guide to transfer learning for text classification using convolutional neural networks. In SDM.","DOI":"10.1137\/1.9781611975321.58"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"J. Shang M. Sun and K. Collins-Thompson. 2018. Demographic inference via knowledge transfer in cross-domain recommender systems. In ICDM.","DOI":"10.1109\/ICDM.2018.00162"},{"key":"e_1_3_2_2_27_1","unstructured":"N. Srivastava G. Hinton A. Krizhevsky I. Sutskever and R. Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. JMLR (2014)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"C. Sun A. Shrivastava S. Singh and A. Gupta. 2017. Revisiting unreasonable effectiveness of data in deep learning era. In ICCV.","DOI":"10.1109\/ICCV.2017.97"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"C. Szegedy V. Vanhoucke S. Ioffe J. Shlens and Z. Wojna. 2016. Rethinking the inception architecture for computer vision. In CVPR.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"P. Vijayaraghavan S. Vosoughi and D. Roy. 2017. Twitter demographic classification using deep multi-modal multi-task learning. In ACL.","DOI":"10.18653\/v1\/P17-2076"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Z. Wang S. Hale D. Adelani P. Grabowicz T. Hartman F. Fl\u00f6ck and D. Jurgens. 2019. Demographic inference and representative population estimates from multilingual social media data. In WWW.","DOI":"10.1145\/3308558.3313684"},{"key":"e_1_3_2_2_32_1","volume-title":"Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196","author":"Wei J.","year":"2019","unstructured":"J. Wei and K. Zou. 2019. Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196 (2019)."},{"key":"e_1_3_2_2_33_1","unstructured":"Y. Xu A. Noy M. Lin Q. Qian H. Li and R. Jin. 2020. WeMix: How to Better Utilize Data Augmentation. arXiv preprint arXiv:2010.01267 (2020)."},{"key":"e_1_3_2_2_34_1","volume":"201","author":"Yurochkin M.","unstructured":"M. Yurochkin, S. Claici, E. Chien, F. Mirzazadeh, and J. Solomon. 2019. Hierarchical optimal transport for document representation. NeurIPS (2019).","journal-title":"J. Solomon."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2465959"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"M. Zhou Z. Li and P. Xie. 2021. Self-supervised Regularization for Text Classification. TACL (2021).","DOI":"10.1162\/tacl_a_00389"}],"event":{"name":"WSDM '23: The Sixteenth ACM International Conference on Web Search and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Singapore Singapore","acronym":"WSDM '23"},"container-title":["Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570462","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570462","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539597.3570462","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:15Z","timestamp":1750186935000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539597.3570462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,27]]},"references-count":36,"alternative-id":["10.1145\/3539597.3570462","10.1145\/3539597"],"URL":"https:\/\/doi.org\/10.1145\/3539597.3570462","relation":{},"subject":[],"published":{"date-parts":[[2023,2,27]]},"assertion":[{"value":"2023-02-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}