Abstract
With the hike of social networking sites like Facebook, Twitter, Instagram, the Marathi web data are increasing day by day. Mining these data towards the corporate and government has become a broad area of research under Natural Language Processing. Sentiment Analysis (SA), identification of the public’s attitude, using machine learning or subjective lexicon, is easier for resource-rich languages like English. Still, for Marathi being poor resource language, it’s a difficult task. In this research, the three approaches have experimented – Corpus-based, SentiWordNet3.0-based, and Hindi SentiWordNet (HSWN)-based to create the Marathi sentiment lexicon (adjective, adverb). The first two approaches use Google Translator to make use of English resource-SWN3.0. The third approach uses HSWN and Marathi WordNet, which minimizes translation errors. The word coverage of the SWN3.0-based lexicon is noteworthy. This paper attempts the Marathi subjective lexicon creation for the first time, which would aid for SA chore precise to the Marathi data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kashyap, L., Joshi, S.R., Bhattacharyya, P.: Insights on Hindi WordNet coming from the IndoWordNet. In: Dash, N.S., Bhattacharyya, P., Pawar, J.D. (eds.) The WordNet in Indian Languages, pp. 19–44. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-1909-8_2
Google Translate. https://translate.google.com
Al-Sallab, A., Baly, R., Hajj, H., Shaban, K.B., El-Hajj, W., Badaro, G.: AROMA: a recursive deep learning model for opinion mining in Arabic as a low resource language. ACM Trans. Asian Low-Resource Lang. Inf. Process. (TALLIP) 16(4), 25:1–25:20 (2017)
Alomari, K.M., ElSherif, H.M., Shaalan, K.: Arabic tweets sentimental analysis using machine learning. In: Benferhat, S., Tabia, K., Ali, M. (eds.) IEA/AIE 2017. LNCS (LNAI), vol. 10350, pp. 602–610. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60042-0_66
Saif M., Salameh, M., Kiritchenko, S.: Sentiment lexicons for Arabic social media. In: Proceedings of the 10th Edition of the Language Resources and Evaluation Conference (LREC), pp. 33–37. Portoroz, Slovenia LREC (2016)
Baccianella, S., Esuli, A., Sebastiani, F.: SentiWordNet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining. In: Proceedings of the Seventh Conference on International Language Resources and Evaluation (LREC 2010), pp. 2200–2204. European Languages Resources Association (ELRA), Valletta, Malta (2010)
Liu, B.: Handbook of Natural Language Processing, 2nd eds. CRC Press, Taylor and Francis Group, Boca Raton (2010)
Medagoda, N., Shanmuganathan, S., Whalley, J.: Sentiment lexicon construction using SentiWordNet 3.0. In: Proceedings of 11th International Conference on Natural Computation (ICNC), pp. 802–807. IEEE, Zhangjiajie (2015)
Bakliwal, A., Arora, P., Varma, V.: Hindi subjective lexicon: a lexical resource for Hindi polarity classification. In: Proceedings of the Eighth International Conference on Language Resources and Evaluation Conference (LREC), pp. 1189–1196. Istanbul, Turkey (2012)
Kim, S.M., Hovy, E.: Identifying and analyzing judgment opinions. In: Proceedings of HLT/NAACL-2006, pp. 200–207. ACL, NY (2006)
Karthikeyan, A.: Hindi English wordnet linkage (2010)
Benamara, F., Cesarano, C., Picariello, A., Reforgiato, D., Subrahmanian, V.: Sentiment analysis: adjectives and adverbs are better than adjectives alone. In: Proceedings of the International Conference on Weblogs and Social Media (ICWSM), pp. 1–7. ICWSM, Boulder, CO (2007)
Mahanty, G., Kannan, A., Mamidi, R.: Building a SentiWordNet for Odia. In: Proceedings of 8th Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis, pp. 143–148. Association for Computational Linguistics (ACL), Copenhagen, Denmark (2017)
Das, A., Bandyopadhyay, S.: SentiWordNet for Indian languages. In: Proceedings of the 8th Workshop on Asian Language Resources, pp. 56–63. Coling 2010 Organizing Committee, Beijing, China (2010)
Popale, L., Bhattacharyya, P.: Creating Marathi WordNet. In: Dash, N.S., Bhattacharyya, P., Pawar, J.D. (eds.) The WordNet in Indian Languages, pp. 147–166. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-1909-8_8
Joshi, A., Balamurali, A.R., Bhattacharyya, P.: A fall-back strategy for sentiment analysis in Hindi: a case study. In: Proceedings 8th International Conference on Natural Language Processing, ICON (2010)
El-Haj, M., Kruschwitz, U., Fox, C.: Creating language resources for under-resourced languages: methodologies, and experiments with Arabic. Lang. Resourc. Eval. 49(3), 549–580 (2014). https://doi.org/10.1007/s10579-014-9274-3
Al-Thubaity, A., Alqahtani, Q., Alijandal, A.: Sentiment lexicon for sentiment analysis of Saudi dialect tweets. In: Proceedings of the Fourth International Conference on Arabic Computational Linguistics (ACLing 2018), pp. 301–307. Elsevier, Dubai, United Arab Emirates (2018)
Wikipedia contributors, “Cohen's kappa” Wikipedia, The Free Encyclopedia. https://en.wikipedia.org/w/index.php?title=Cohen%27s_kappa&oldid=928044732. Accessed 29 Nov 2019
Xu, G., Yu, Z., Yao, H., Li, F., Meng, Y., Xu, W.: Chinese text sentiment analysis based on extended sentiment dictionary. IEEE Access 7, 43749–43762 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Patil, R.S., Kolhe, S.R. (2021). Resource Creation for Sentiment Analysis of Under-Resourced Language: Marathi. In: Santosh, K.C., Gawali, B. (eds) Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2020. Communications in Computer and Information Science, vol 1380. Springer, Singapore. https://doi.org/10.1007/978-981-16-0507-9_37
Download citation
DOI: https://doi.org/10.1007/978-981-16-0507-9_37
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-0506-2
Online ISBN: 978-981-16-0507-9
eBook Packages: Computer ScienceComputer Science (R0)