Exploring Mechanisms for Detecting Violent Content in Sinhala Image Posts: Rationale with Unsupervised vs Supervised Techniques
Abstract
This research explores the different avenues in machine learning to classify Sinhala image posts. Image posts in social media are one big weapon that conveys information directly to people. Image posts contain both visuals and text. English based research work is common in this regard, but only a handful can be seen from other languages. The target language was a low-resource language, Sinhala. Unsupervised algorithms were used to classify image posts and supervised algorithms were involved classifying manually extracted text in image posts. The classification decides whether the posts are violent or nonviolent. The trained supervised models were tested with interpretability models to identify the words that cause the decision of violent or nonviolent. The findings reveal supervised algorithms perform better than unsupervised algorithms in classifying image posts. However, improved results can be obtained by increasing the size and the variety of the dataset.
References
Aggarwal C.C., Sathe S.: Theoretical foundations and algorithms for outlier ensembles. In: Acm sigkdd explorations newsletter, vol. 17(1), pp. 24--47, 2015.
Aktı S., Ofli F., Imran M., Ekenel H.K.: Fight detection from still images in the wild. In: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp. 550--559. 2022.
Amorim M., Bortoloti F.D., Ciarelli P.M., Salles E.O., Cavalieri D.C.: Novelty detection in social media by fusing text and image into a single structure. In: IEEE Access, vol. 7, pp. 132786--132802, 2019.
Amos B., Ludwiczuk B., Satyanarayanan M., et al.: Openface: A general-purpose face recognition library with mobile applications. In: CMU School of Computer Science, vol. 6(2), p. 20, 2016.
Badjatiya P., Gupta S., Gupta M., Varma V.: Deep learning for hate speech detection in tweets. In: Proceedings of the 26th international conference on World Wide Web companion, pp. 759--760. 2017.
Bharti: Sentimental with Multi Layer Bi directional RNN using PyTorch, 2020. URL {https://medium.com/@bhartikukreja2015/ sentimental-with-multi-layer-bi-directional-rnn-using-pytorch-4f386297a0fc}.
Blandfort P., Patton D.U., Frey W.R., Karaman S., Bhargava S., Lee F.T., Varia S., Kedzie C., Gaskell M.B., Schifanella R., et al.: Multimodal social media analysis for gang violence prevention. In: Proceedings of the International AAAI conference on web and social media, vol. 13, pp. 114--124. 2019.
Bojanowski P., Grave E., Joulin A., Mikolov T.: Enriching word vectors with subword information. In: Transactions of the association for computational linguistics, vol. 5, pp. 135--146, 2017.
Breiman L.: Random forests. In: Machine learning, vol. 45, pp. 5--32, 2001.
Chhabra A., Vishwakarma D.K.: A literature survey on multimodal and multilingual automatic hate speech identification. In: Multimedia Systems, pp. 1--28, 2023.
Chung J., Gulcehre C., Cho K., Bengio Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: arXiv preprint arXiv:1412.3555, 2014.
Cohen J.: A coefficient of agreement for nominal scales. In: Educational and psycho logical measurement, vol. 20(1), pp. 37--46, 1960.
Conneau A., Lample G.: Cross-lingual language model pretraining. In: Advances in neural information processing systems, vol. 32, 2019.
Cramer J.S.: The origins of logistic regression. In: , 2002.
Davidson T., Warmsley D., Macy M., Weber I.: Automated hate speech detection and the problem of offensive language. In: Proceedings of the international AAAI conference on web and social media, vol. 11, pp. 512--515. 2017.
Demotte P., Senevirathne L., Karunanayake B., Munasinghe U., Ranathunga S.: SEN CAT Tool for Sinhala Sentiment Analysis, 2020. URL https://sencat.lk/.
Devlin J., Chang M.W., Lee K., Toutanova K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: arXiv preprint arXiv:1810.04805, 2018.
Dhananjaya V., Demotte P., Ranathunga S., Jayasena S.: BERTifying Sinhala--A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification. In: arXiv preprint arXiv:2208.07864, 2022.
Dias D.S., Welikala M.D., Dias N.G.: Identifying racist social media comments in sinhala language using text analytics models with machine learning. In: 2018 18th International Conference on Advances in ICT for Emerging Regions (ICTer), pp. 1--6. IEEE, 2018.
Dikwatta U., Fernando T.: Violence Detection of Sinhala Image Posts with Autoencoders. In: 2021 10th International Conference on Information and Automation for Sustainability (ICIAfS), pp. 275--280. IEEE, 2021.
Djuric N., Zhou J., Morris R., Grbovic M., Radosavljevic V., Bhamidipati N.: Hate speech detection with comment embeddings. In: Proceedings of the 24th international conference on world wide web, pp. 29--30. 2015.
Edunov S., Ott M., Auli M., Grangier D.: Understanding back-translation at scale. In: arXiv preprint arXiv:1808.09381, 2018.
Fortuna P., Nunes S.: A survey on automatic detection of hate speech in text. In: ACM Computing Surveys (CSUR), vol. 51(4), pp. 1--30, 2018.
Graves A., Schmidhuber J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. In: Neural networks, vol. 18(5-6), pp. 602--610, 2005.
Haque R., Islam N., Tasneem M., Das A.K.: MULTI-CLASS SENTIMENT CLASSIFICATION ON BENGALI SOCIAL MEDIA COMMENTS USING MACHINE LEARNING. In: International Journal of Cognitive Computing in Engineering, 2023.
He K., Gkioxari G., Dollár P., Girshick R.: Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp. 2961--2969. 2017.
Hochreiter S., Schmidhuber J.: Long short-term memory. In: Neural computation, vol. 9(8), pp. 1735--1780, 1997.
Hossin M., Sulaiman M.N.: A review on evaluation metrics for data classification evaluations. In: International journal of data mining & knowledge management process, vol. 5(2), p. 1, 2015.
Jallad K.A., Ghneim N.: ArNLI: Arabic Natural Language Inference for Entailment and Contradiction Detection. In: arXiv preprint arXiv:2209.13953, 2022.
Kaplan A.M., Haenlein M.: Users of the world, unite! The challenges and opportunities of Social Media. In: Business horizons, vol. 53(1), pp. 59--68, 2010.
Le Q., Mikolov T.: Distributed representations of sentences and documents. In: International conference on machine learning, pp. 1188--1196. PMLR, 2014.
Le Cam L.: Maximum likelihood: an introduction. In: International Statistical Review/Revue Internationale de Statistique, pp. 153--171, 1990.
Lundberg S.M., Lee S.I.: A unified approach to interpreting model predictions. In: Advances in neural information processing systems, vol. 30, 2017.
Malik J.S., Pang G., Hengel A.v.d.: Deep learning for hate speech detection: a comparative study. In: arXiv preprint arXiv:2202.09517, 2022.
Malmasi S., Tetreault J., Dras M.: Oracle and human baselines for native language identification. In: Proceedings of the tenth workshop on innovative use of NLP for building educational applications, pp. 172--178. 2015.
Malmasi S., Zampieri M.: Detecting hate speech in social media. In: arXiv preprint arXiv:1712.06427, 2017.
Mazari A.C., Boudoukhani N., Djeffal A.: BERT-based ensemble learning for multi aspect hate speech detection. In: Cluster Computing, pp. 1--15, 2023.
Meyer D., Wien F.: Support vector machines. In: The Interface to libsvm in package e1071, vol. 28, p. 20, 2015.
Mikolov T., Chen K., Corrado G., Dean J.: Efficient estimation of word representations in vector space. In: arXiv preprint arXiv:1301.3781, 2013.
Mikolov T., Chen K., Corrado G., Dean J.: Efficient estimation of word representations in vector space. In: arXiv preprint arXiv:1301.3781, 2013.
Mozafari M., Farahbakhsh R., Crespi N.: A BERT-based transfer learning approach for hate speech detection in online social media. In: Complex Networks and Their Applications VIII: Volume 1 Proceedings of the Eighth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2019 8, pp. 928--940. Springer, 2020.
Naher J., Minar M.R.: Impact of social media posts in real life violence: A case study in Bangladesh. In: arXiv preprint arXiv:1812.08660, 2018.
Omar A., Mahmoud T.M., Abd-El-Hafeez T.: Comparative performance of machine learning and deep learning algorithms for Arabic hate speech detection in osns. In: Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020), pp. 247--257. Springer, 2020.
Omar A., Mahmoud T.M., Abd-El-Hafeez T., Mahfouz A.: Multi-label arabic text classification in online social networks. In: Information Systems, vol. 100, p. 101785, 2021.
Orru P., et al.: Racist discourse on social networks: A discourse analysis of Facebook posts in Italy. In: Rhesis, vol. 5(1), pp. 113--133, 2015.
Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., et al.: Scikit-learn: Machine learning in Python. In: the Journal of machine Learning research, vol. 12, pp. 2825--2830, 2011.
Prechelt L.: Early stopping-but when? In: Neural Networks: Tricks of the trade, pp. 55--69. Springer, 2002.
Ranathunga S., Liyanage I.U.: Sentiment analysis of sinhala news comments. In: Transactions on Asian and Low-Resource Language Information Processing, vol. 20(4), pp. 1--23, 2021.
Rathnayake H., Sumanapala J., Rukshani R., Ranathunga S.: Adapter-based fine-tuning of pre-trained multilingual language models for code-mixed and code-switched text classification. In: Knowledge and Information Systems, vol. 64(7), pp. 1937--1966, 2022.
Ribeiro M.T., Singh S., Guestrin C.: ``Why should i trust you?'' Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp. 1135--1144. 2016.
Ruder S.: An overview of gradient descent optimization algorithms. In: arXiv preprint arXiv:1609.04747, 2016.
Ruwandika N., Weerasinghe A.: Identification of hate speech in social media. In: 2018 18th international conference on advances in ICT for emerging regions (ICTer), pp. 273- -278. IEEE, 2018.
Samarasinghe S., Meegama R., Punchimudiyanse M.: Machine learning approach for the detection of hate speech in sinhala unicode text. In: 2020 20th International Conference on Advances in ICT for Emerging Regions (ICTer), pp. 65--70. IEEE, 2020.
Sandaruwan S.T., Lorensuhewa S.A.S., Munasinghe K.: Identification of abusive sinhala comments in social media using text mining and machine learning techniques. In: The International Journal on Advances in ICT for Emerging Regions, vol. 13(1), 2020.
Schmidt A., Wiegand M.: A survey on hate speech detection using natural language processing. In: Proceedings of the fifth international workshop on natural language processing for social media, pp. 1--10. 2017.
Senarath Y.: A language processing tool for Sinhalese, 2004. URL https://sinling. ysenarath.com/.
Senevirathne L., Demotte P., Karunanayake B., Munasinghe U., Ranathunga S.: Sentiment analysis for sinhala language using deep learning techniques. In: arXiv preprint arXiv:2011.07280, 2020.
Shorten C., Khoshgoftaar T.M.: A survey on image data augmentation for deep learning. In: Journal of big data, vol. 6(1), pp. 1--48, 2019.
Silva E., Nandathilaka M., Dalugoda S., Amarasinghe T., Ahangama S., Weerasuriya G.T.: Machine Learning-Based Automated Tool to Detect Sinhala Hate Speech in Images. In: 2021 6th International Conference on Information Technology Research (IC ITR), pp. 1--7. IEEE, 2021.
Sun S., Liu Y., Mao L.: Multi-view learning for visual violence recognition with maximum entropy discrimination and deep features. In: Information Fusion, vol. 50, pp. 43--53, 2019.
Sundararajan M., Taly A., Yan Q.: Axiomatic attribution for deep networks. In: International conference on machine learning, pp. 3319--3328. PMLR, 2017.
Sunde B.M.: Early Stopping for PyTorch, 2020. URL https://github.com/ Bjarten/early-stopping-pytorch.
Suryawanshi S., Chakravarthi B.R., Arcan M., Buitelaar P.: Multimodal meme dataset (MultiOFF) for identifying offensive content in image and text. In: Proceedings of the second workshop on trolling, aggression and cyberbullying, pp. 32--41. 2020.
Tran C.: A Complete Guide to CNN for Sentence Classification with PyTorch, 2020. URL https://chriskhanhtran.github.io/posts/ cnn-sentence-classification/.
Uppada S.K., Patel P.: An image and text-based multimodal model for detecting fake news in OSN?s. In: Journal of Intelligent Information Systems, pp. 1--27, 2022.
Vajjala S., Majumder B., Gupta A., Surana H.: Practical natural language processing: a comprehensive guide to building real-world NLP systems. O'Reilly Media, 2020.
Waseem Z., Hovy D.: Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In: Proceedings of the NAACL student research workshop, pp. 88--93. 2016.
Waseem Z., Thorne J., Bingel J.: Bridging the gaps: Multi task learning for domain transfer of hate speech detection. In: Online harassment, pp. 29--55, 2018.
Watanabe H., Bouazizi M., Ohtsuki T.: Hate speech on twitter: A pragmatic approach to collect hateful and offensive expressions and perform hate speech detection. In: IEEE access, vol. 6, pp. 13825--13835, 2018.
Webb G.I.: Decision tree grafting from the all-tests-but-one partition. In: Ijcai, vol. 2, pp. 702--707. 1999.
Wolf T., Debut L., Sanh V., Chaumond J., Delangue C., Moi A., Cistac P., Rault T., Louf R., Funtowicz M., Davison J., Shleifer S., von Platen P., Ma C., Jernite Y., Plu J., Xu C., Scao T.L., Gugger S., Drame M., Lhoest Q., Rush A.M.: HuggingFace's Transformers: State-of-the-art Natural Language Processing, 2019. URL http://dx.doi.org/10. 48550/ARXIV.1910.03771.
Won D., Steinert-Threlkeld Z.C., Joo J.: Protest activity detection and perceived violence estimation from social media images. In: Proceedings of the 25th ACM international conference on Multimedia, pp. 786--794. 2017.
Zhang Z., Luo L.: Hate speech detection: A solved problem? the challenging case of long tail on twitter. In: Semantic Web, vol. 10(5), pp. 925--945, 2019.
Šolc T.: Unidecode, lossy ASCII transliterations of Unicode text, 2022. URL https: //github.com/avian2/unidecode.
