Abstract
Sentiment analysis is among the main targets of natural language processing (NLP) that assigns a positive or negative value to the opinion expressed in natural language text within different contexts such as social media, forum, news, blogs, and many others. Sentiments of an under-researched language such as Amharic have received little attention in NLP applications due to the scares of enough resources to develop such methods. In this paper we combine the deep learning (CNN, LSTM, FFNN, and BiLSTM) and classical models (cosine similarity) with word embedding techniques for sentence-level sentiment classification of social media messages in Amharic language that has never been tested before. We use the Amharic Twitter dataset that consists of around 3000 text snippets. Data augmentation is applied to increase the dataset for training those models. We achieved the 82.2% accuracy using the sentence transformer and cosine similarity on the Amharic corpus.
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
References
Ji, Z., Pi, H., Wei, W., Xiong, B., Wozniak, M., Damasevicius, R.: Recommendation based on review texts and social communities: a hybrid model. IEEE Access 7, 40416–40427 (2019). https://doi.org/10.1109/ACCESS.2019.2897586
Behera, R.K., Das, S., Rath, S.K., Misra, S., Damasevicius, R.: Comparative study of real time machine learning models for stock prediction through streaming data. J. Universal Comput. Sci. 26(9), 1128–1147 (2020)
Vaiciukynaite, E., Zailskaite-Jakste, L., Damasevicius, R., Gatautis, R.: Does hedonic content of brand posts affect consumer sociability behaviour on Facebook? In: Proceedings of the 5th European Conference on Social Media, ECSM 2018, pp. 325–331 (2018)
Okewu, E., Misra, S., Okewu, J., Damaševičius, R., Maskeliūnas, R.: An intelligent advisory system to support managerial decisions for a social safety net. Adm. Sci. 9(3), 55 (2019). https://doi.org/10.3390/admsci9030055
Omoregbe, N.A.I., Ndaman, I.O., Misra, S., Abayomi-Alli, O.O., Damaševičius, R.: Text messaging-based medical diagnosis using natural language processing and fuzzy logic. J. Healthc. Eng. 2020, 1–14 (2020). https://doi.org/10.1155/2020/8839524
Aldjanabi, W., Dahou, A., Al-Qaness, M.A.A., Elaziz, M.A., Helmi, A.M., Damaševičius, R.: Arabic offensive and hate speech detection using a cross-corpora multi-task learning model. Informatics 8(4), 69 (2021). https://doi.org/10.3390/informatics8040069
Tesfagergish, S.G., Damaševičius, R., Kapočiūtė-Dzikienė, J.: Deep fake recognition in tweets using text augmentation, word embeddings and deep learning. In: Gervasi, O., et al. (eds.) ICCSA 2021. LNCS, vol. 12954, pp. 523–538. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86979-3_37
Venčkauskas, A., Damaševičius, R., Marcinkevičius, R., Karpavičius, A.: Problems of authorship identification of the national language electronic discourse. In: Dregvaite, G., Damasevicius, R. (eds.) ICIST 2015. CCIS, vol. 538, pp. 415–432. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24770-0_36
Choi, M., Shin, J., Kim, H.: Robust feature extraction method for automatic sentiment classification of erroneous online customer reviews. Information (Japan) 16(10), 7637–7646 (2013)
Gereme, F., Zhu, W., Ayall, T., Alemu, D.: Combating fake news in “low-resource” languages: amharic fake news detection accompanied by resource crafting. Information 12, 20 (2021). https://doi.org/10.3390/info12010020
Nandwani, P., Verma, R.: A review on sentiment analysis and emotion detection from text. Soc. Netw. Anal. Min. 11(1), 1–19 (2021). https://doi.org/10.1007/s13278-021-00776-6
Kapočiūtė-Dzikienė, J., Damaševičius, R., Woźniak, M.: Sentiment analysis of Lithuanian texts using traditional and deep learning approaches. Computers 8(1), 4 (2019)
Yimam, S.M., Alemayehu, H.M., Ayele, A., Biemann, C.: Exploring amharic sentiment analysis for social media texts: building annotation tools and classification models. In: Proceeding of the 28th International Conference on Computational Linguistics (2020)
Getachew, Y., Alemu, A.: Deep learning approach for amharic sentiment analysis. University Of Gondar (2018)
Wondwossen, P., Wondwossen, M.: A machine learning approach to multi-scale sentiment analysis of amharic online posts. HiLCoE J. Comput. Sci. Technol. 2(2), 8 (2014)
Neshir, G., Atnafu, S., Rauber, A.: BERT fine-tuning for amharic sentiment classification. In: Workshop RESOURCEFUL Co-Located with the Eighth Swedish Language Technology Conference (SLTC), Gothenburg, Sweden, 25 November 2020 (2020)
Heikal, M., Torki, M., El-Makky, N.: Sentiment analysis of Arabic tweets using deep learning. Proc. Comput. Sci. 142, 114–122 (2018)
Ombabi, A.H., Ouarda, W., Alimi, A.M.: Deep learning CNN–LSTM framework for Arabic sentiment analysis using textual information shared in social networks. Soc. Netw. Anal. Min. 10(1), 1–13 (2020). https://doi.org/10.1007/s13278-020-00668-1
Tang, D., Qin, B., Liu, T.: Deep learning for sentiment analysis: successful approaches and future challenges. Wiley Interdiscipl. Rev. Data Min. Knowl. Discov. 5(6), 292–303 (2015)
Yimam, S.M., Ayele, A.A., Biemann, C.: Analysis of the ethiopic Twitter dataset for abusive speech in amharic. In: International Conference on Language Technologies for All: Enabling Linguistic Diversity And Multilingualism Worldwide, Paris, France, pp. 1–5 (2019)
Kaggle. Sentiment140 Dataset with 1.6 Million Tweets. https://www.kaggle.com/kazanova/sentiment140. Accessed 8 Jan 2022
Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (2019)
Feng, F., Yang, Y., Cer, D., Arivazhagan, N., Wang, W.: Language-agnostic BERT sentence embedding. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2022). https://doi.org/10.18653/v1/2022.acl-long.62
Pota, M., Ventura, M., Catelli, R., Esposito, M.: An effective BERT-based pipeline for twitter sentiment analysis: a case study in Italian. Sensors 21(1), 1–21 (2021)
Go, A., Bhayani, R., Huang, L.: Twitter sentiment classification using distant supervision. CS224N Project Report, Stanford, 1(2009), p. 12 (2009)
Tesfagergish, S.G., Kapočiūtė-Dzikienė, J., Damaševičius, R.: Zero-shot emotion detection for semi-supervised sentiment analysis using sentence transformers and ensemble learning. Appl. Sci. 12, 8662 (2022). https://doi.org/10.3390/app12178662
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tesfagergish, S.G., Damaševičius, R., Kapočiūtė-Dzikienė, J. (2022). Deep Learning-Based Sentiment Classification of Social Network Texts in Amharic Language. In: Zdravkova, K., Basnarkov, L. (eds) ICT Innovations 2022. Reshaping the Future Towards a New Normal. ICT Innovations 2022. Communications in Computer and Information Science, vol 1740. Springer, Cham. https://doi.org/10.1007/978-3-031-22792-9_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-22792-9_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22791-2
Online ISBN: 978-3-031-22792-9
eBook Packages: Computer ScienceComputer Science (R0)