Şeref KESKİN, Mehmet APAYDIN, Işılay TUNCER

İşin Olsun Platformu İlanlarında İçerik Kontrolü

Bu bildiride mavi yakalı iş arama ve bulma platformu olan İşin Olsun sitesindeki ilanların içerik yönetimi ve otomatik içerik kontrolü hakkında geliştirilen yaklaşımlar açıklanacaktır. Bu amaçla denetimli makine öğrenmesi modelleri ve Bert transformer mimarisi yöntemleri ile deneyler gerçekleştirilerek sonuçları gözlemlenmiştir. Çalışma sonunda, en başarılı yöntem Bert for sequence classification kullanılarak ilan içeriklerinin otomatik olarak sınıflandırıldığı bir sistem geliştirilmiş ve bu sistem iş arama platformuna entegre edilmiştir. İşin Olsun ilan metinlerinin kontrolör görevindeki kişiler tarafından uygun veya uygun olmayan içerik şeklinde iki farklı sınıfta etiketlenmesinden başlayarak, veri kümesinin hazırlanma aşamalarından, sınıflandırma modelinin sisteme entegrasyonuna kadar olan çalışmalar bu bildiride özetlenmektedir.

Anahtar Kelimeler:

dil modelleri, bert, transformers, doğal dil işleme, yapay zekâ, derin öğrenme

Content Control in İşin Olsun Platform Job Texts

In this paper, the approaches developed for the content management and automatic content control of the postings on the İşin Olsun website, which is a blue-collar job search and finding platform, will be explained. For this purpose, experiments were carried out with supervised machine learning models and Bert transformer architecture methods and the results were observed. At the end of the study, a system was developed in which the contents of the job texts are automatically classified using Bert for sequence classification, which was determined as the most successful method, and this system was integrated into the job search platform. Starting from labeling the job texts in two different classes as appropriate or unsuitable content by the controllers, from the preparation stages of the dataset to the integration of the classification model into the system, the studies are summarized in this paper.

Keywords:

language models, bert, transformers, natural language processing, artificial intelligence, deep learning,

PDF

___

[Online]. Available: https://isinolsun.com/
U. U. Acikalin, B. Bardak, and M. Kutlu, “Turkish sentiment analysis using bert,” in 2020 28th Signal Processing and Communications Applications Conference (SIU), 2020, pp. 1–4.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” 2019.
Y. Zhang, R. Jin, and Z.-H. Zhou, “Understanding bag-of-words model: A statistical framework,” International Journal of Machine Learning and Cybernetics, vol. 1, pp. 43–52, 12 2010.
[Online]. Available: https://huggingface.co/transformers/model doc/bert. html
S. Schweter, “Berturk - bert models for turkish,” Apr. 2020. [Online]. Available: https://doi.org/10.5281/zenodo.3770924
[Online]. Available: https://www.perspectiveapi.com/
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” 2017. [Online]. Available: https://arxiv.org/pdf/1706.03762.pdf
[Online]. Available: https://en.wikipedia.org/wiki/Scunthorpe problem
C. Sun, X. Qiu, Y. Xu, and X. Huang, “How to fine-tune bert for text classification?” 2020.
G. Dogan, N. Alotaibi, E. Sahin, S. S. Ertas, I. Cay, R. Keskin, M. J. H. Heijnen, and K. Ricanek, “Using artificial intelligence to predict fall-risk during adaptive locomotion in humans,” in 2020 International Confer- ence on Artificial Intelligence Modern Assistive Technology (ICAIMAT), 2020, pp. 1–7.
G. M. Demirci, R. Keskin, and G. Dog ̆an, “Sentiment analysis in turkish with deep learning,” in 2019 IEEE International Conference on Big Data (Big Data), 2019, pp. 2215–2221.