Abstract
We present annotation results for a dataset of public anonymous online confessions in Russian (“Overheard/Podslushano” group in VKontakte, posts tagged #family). Unlike many other cases with online social network data, intentionally anonymous posts do not contain any explicit metadata such as age or gender. We consider the problem of predicting the author’s preferred grammatical gender for self-reference, a problem that proved to be surprisingly hard and not reducible to simple morphological analysis. We describe an expert labeling of a dataset for this problem, show the findings of predictive analysis, and introduce rule-based and machine learning approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
https://vk.com/overhear, with more than 3,987,000 users reading the community as of February 20, 2020.
- 2.
We have made several attempts to tackle the annotation task via crowdsourcing platforms, updating the instructions and adding more advanced qualification tests. However, most annotators still derived the gender based on stereotypes, so we had to ask our own experts to label the data, which explains the modest size of the corpus.
- 3.
We have used tokens and bigrams available in the training set with the minimum document frequency of 3; scikit-learn’s [11] default TF-IDF weighting scheme was employed.
- 4.
As of June 11, 2020, the model is available at: https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3131.
- 5.
Originally in Russian, translated into English.
References
ELI5: a Python package to debug machine learning classifiers and explain their predictions (2016). https://github.com/TeamHG-Memex/eli5/
Akiba, T., Sano, S., Yanase, T., Ohta, T., Koyama, M.: Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2019)
Alekseev, A., Nikolenko, S.: Word embeddings for user profiling in online social networks. Computación y Sistemas 21(2), 203–226 (2017)
Anastasyev, D., Gusev, I., Indenbom, E.: Improving part-of-speech tagging via multi-task learning and character-level word representations. arXiv preprint arXiv:1807.00818 (2018)
Christopherson, K.M.: The positive and negative implications of anonymity in internet social interactions: “on the internet, nobody knows you’re a dog”. Comput. Hum. Behav. 23(6), 3038–3056 (2007)
Kang, R., Brown, S., Kiesler, S.: Why do people seek anonymity on the internet? informing policy and design. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 2657–2666 (2013)
Ke, G., et al.: Lightgbm: a highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems, pp. 3146–3154 (2017)
Kestemont, M., et al.: Overview of the author identification task at pan-2018: cross-domain authorship attribution and style change detection. In: Working Notes Papers of the CLEF 2018 Evaluation Labs. Avignon, France, 10–14 September, 2018/Cappellato, Linda [edit.] et al, pp. 1–25 (2018)
Meng, Q., et al.: A communication-efficient parallel algorithm for decision tree. In: Advances in Neural Information Processing Systems, pp. 1279–1287 (2016)
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Rangel, F., Rosso, P., Potthast, M., Stein, B.: Overview of the 5th author profiling task at pan 2017: Gender and language variety identification in twitter. Working Notes Papers of the CLEF, pp. 1613–0073 (2017)
Rogers, A., Romanov, A., Rumshisky, A., Volkova, S., Gronas, M., Gribov, A.: Rusentiment: an enriched sentiment analysis dataset for social media in Russian. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 755–763 (2018)
Straka, M., Straková, J.: Tokenizing, POS tagging, lemmatizing and parsing UD 2.0 with udpipe. In: Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pp. 88–99. Association for Computational Linguistics, Vancouver, Canada, August 2017
Straka, M., Straková, J.: Universal dependencies 2.5 models for UDPipe (2019–12-06) (2019), http://hdl.handle.net/11234/1-3131, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R.R., Le, Q.V.: XLNET: generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems, pp. 5754–5764 (2019)
Acknowledgement
This work was carried out at the Samsung-PDMI Joint AI Center at Steklov Mathematical Institute at St. Petersburg and supported by Samsung Research. We would like to thank anonymous reviewers for insightful comments that helped us to improve the paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: instructions for annotation
Appendix: instructions for annotation
Which grammatical gender do authors use when talking about themselves?Footnote 5
Short description: We ask you to carefully read the short text and report in what grammatical gender the authors refer to themselves, based on grammatical evidence/clues.
It is usually clear which grammatical gender (feminine/masculine/etc.) the users prefer when speaking about themselves in their posts. However, sometimes it may be impossible. Not all cases are obvious, please do read the instructions.
IMPORTANT: only grammatical features and clues can be used to determine the gender. The task is not to guess whether a man or a woman wrote the text. The task is to determine with confidence which grammatical gender they prefer when talking about themselves.
Sample cases with possible errors.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Alekseev, A., Nikolenko, S. (2020). Recognizing Preferred Grammatical Gender in Russian Anonymous Online Confessions. In: Sojka, P., Kopeček, I., Pala, K., Horák, A. (eds) Text, Speech, and Dialogue. TSD 2020. Lecture Notes in Computer Science(), vol 12284. Springer, Cham. https://doi.org/10.1007/978-3-030-58323-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-58323-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58322-4
Online ISBN: 978-3-030-58323-1
eBook Packages: Computer ScienceComputer Science (R0)