DSpace Repository

Restoran Müşterilerinin Geri Bildirimleri Üzerinde Hedef Kategorinin Tespiti ve Hedef Tabanlı Duygu Analizi

Show simple item record

dc.creator Tuna, Murat Fatih
dc.creator Polatgil, Mesut
dc.creator Kaynar, Oğuz
dc.date 2022-11-22
dc.date.accessioned 2025-02-25T10:51:11Z
dc.date.available 2025-02-25T10:51:11Z
dc.identifier https://dergipark.org.tr/tr/pub/vizyoner/issue/80965/1208355
dc.identifier 10.21076/vizyoner.1208355
dc.identifier.uri http://acikerisim.sdu.edu.tr/xmlui/handle/123456789/103140
dc.description Günümüzde tüketicilerin ürün ve hizmetler konusunda fikir paylaşabilecekleri birçok mecra bulunmaktadır. Bu fikirler, geri bildirimin yapısı itibariyle genellikle metin formatındadır. Duygu analizi, metin tabanlı bilgi kaynaklarında son yıllarda önem kazanan bir konudur. Daha hassas bir duygu analiz türü olan Hedef Tabanlı Duygu Analizi bir cümle içerisinde hedef terim, hedef kategori ve duygu sınıfının belirlenmesi işidir. Bu çalışmada Semeval ABSA yarışmasında yarışmacılara sunulan restoran müşterilerine ait yorumlardan oluşan bir veri seti kullanılmıştır. Word2vec, Glove, Fastext ve Bert yöntemleri kullanılarak veri seti üzerinde hedef terim, hedef kategori ve duygu sınıfının belirlenmesi işlemi gerçekleştirilmiştir. Kelimeyi vektörü ile cümle vektörünün birleştirilmesi ABSA için sınıflandırma başarısını artırıp artıramayacağı hipotezi test edilmiştir. Dört farklı vektör yöntemi ile yapılan sınıflandırmada hedef terim için 0,78 F1 skoru ile Fasttext yöntemi, hedef kategori için 0,57 F1 skoru ile Fasttext ve duygu sınıfı için 0,76 F1 skoru ile Bert yöntemi en başarılı sonuçları vermiştir. Bu sonuçlar literatürde farklı veri setleri ve farklı diller için yapılan çalışmalarla kıyaslanmıştır. Sonuç olarak Fasttext ve Bert temsil yöntemlerinin hedef tabanlı Türkçe dilindeki metinlerin duygu analizinde başarılı sonuçlar verdiği tespit edilmiştir.
dc.description Today, there are many channels where consumers can share their ideas about products and services. These opinions are usually in text format due to the nature of the feedback. Sentiment analysis is a topic that has gained importance in recent years, especially in text-based information sources. Aspect-based Sentiment Analysis, which is a more sensitive sentiment analysis technique, is the task of determining the aspect term, aspect category and sentiment class in a sentence. A data set consisting of the comments of restaurant customers presented to the competitors in the Semeval ABSA competition is used in the study. Using Word2vec, Glove, Fastext and Bert methods, the aspect term, aspect category and sentiment class are determined on the data set. The hypothesis is tested whether combining the word vector and the sentence vector can improve classification success for ABSA. In the classification made with four different vector methods, Fasttext method with 0.78 F1 score for the target term, Fasttext with 0.57 F1 score for the target category, and Bert method with 0.76 F1 score for the sentiment class have the most successful results. These results are compared with studies in the literature for different data sets and different languages. As a result, it is determined that Fasttext and Bert representation methods give successful results in sentiment analysis of target-based Turkish language texts.
dc.format application/pdf
dc.language tur
dc.publisher Süleyman Demirel Üniversitesi
dc.publisher Süleyman Demirel University
dc.relation https://dergipark.org.tr/tr/download/article-file/2787445
dc.source Volume: 14, Issue: 401205-1221 en-US
dc.source 1308-9552
dc.source Süleyman Demirel University Visionary Journal eng
dc.source Süleyman Demirel Üniversitesi Vizyoner Dergisi tur
dc.subject Restoran yorumları;Hedef Tabanlı Duygu Analizi;Fasttext;Bert
dc.subject Restaurant Reviews;Aspect Based Sentiment Analysis;Fasttext;Bert
dc.subject Business Administration
dc.subject İşletme
dc.title Restoran Müşterilerinin Geri Bildirimleri Üzerinde Hedef Kategorinin Tespiti ve Hedef Tabanlı Duygu Analizi tr-TR
dc.title Detection of Aspect Category and Aspect-Based Sentiment Analysis on Restaurant Customers' Feedbacks en-US
dc.type info:eu-repo/semantics/article
dc.citation Ahuja, V. ve Medury, Y. (2010). Corporate blogs as e-CRM tools – building consumer engagement through content management. Journal of Database Marketing & Customer Strategy Management, 17(2), 91-105.
dc.citation Akın, M. D. ve Akın, A. A. (2007). Türk dilleri için açık kaynaklı doğal dil işleme kütüphanesi: ZEMBEREK. Elektrik mühendisliği, 431, 38-44.
dc.citation Barger, V., Peltier, J. W. ve Schultz, D. E. (2016). Social media and consumer engagement: A review and research agenda. Journal of Research in Interactive Marketing, 10(4), 268-287.
dc.citation Bayraktar, K., Yavanoglu, U. ve Ozbilen, A. (2019). A rule-based holistic approach for Turkish aspect-based sentiment analysis. 2019 IEEE International Conference on Big Data (s. 2154-2158). Los Angeles, CA, USA.
dc.citation Berger, J. ve Iyengar, R. (2013). Communication channels and word of mouth: how the medium shapes the message. Journal of Consumer Research, 40(3), 567-579.
dc.citation Brun, C., Popa, D. N. ve Roux, C. (2014). XRCE: hybrid classification for aspect-based sentiment analysis. Proceedings of the 8th International Workshop on Semantic Evaluation (s. 838-842). Dublin, Ireland.
dc.citation Castellucci, G., Filice, S., Croce, D. ve Basili, R. (2014). UNITOR: aspect based sentiment analysis with structured learning. Proceedings of the 8th International Workshop on Semantic Evaluation (s. 761-767). Dublin, Ireland.
dc.citation Chen, P.-Y., Wu, S. ve Yoon, J. (2004). The impact of online recommendations and consumer feedback on Sales. ICIS 2004 Proceedings (s. 711–724). Washington, DC, USA.
dc.citation Chen, Z. ve Qian, T. (2020). Enhancing aspect term extraction with soft prototypes. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (s. 2107-2117). Punta Cana, Dominican Republic.
dc.citation Coşgun, E., Çelebi, A. ve Güllü, M. K. (3-5 Ekim 2019). Dengesiz Veri Kümeleri İçin Epileptik Nöbet Tahmini, Tıp Teknolojileri Kongresi, Kuşadası/Aydın.
dc.citation Çeti̇n, F. S. ve Eryi̇ği̇t, G. (2018). Türkçe hedef tabanlı duygu analizi için alt görevlerin incelenmesi – hedef terim, hedef kategori ve duygu sınıfı belirleme. Bilişim Teknolojileri Dergisi, 11(1), 43-56.
dc.citation Çiftçi, O. (2022). Türkçe GloVe - Repository for Turkish GloVe word embedding. https://github.com/inzva/Turkish-GloVe adresinden 18 Ekim 2022 tarihinde alınmıştır.
dc.citation de Oliveira Santini, F., Ladeira, W. J., Pinto, D. C., Herter, M. M., Sampaio, C. H. ve Babin, B. J. (2020). Customer engagement in social media: A framework and meta-analysis. Journal of the Academy of Marketing Science, 48(6), 1211-1228.
dc.citation Do, H. H., Prasad, P., Maag, A. ve Alsadoon, A. (2019). Deep learning for aspect-based sentiment analysis: A comparative review. Expert Systems with Applications, 118, 272-299.
dc.citation Fan, Z., Wu, Z., Dai, X.-Y., Huang, S. ve Chen, J. (2019). Target-oriented opinion words extraction with target-fused neural sequence labeling. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume I (s. 2509-2518). Minneapolis, MN, USA.
dc.citation Ghadery, E., Movahedi, S., Jalili Sabet, M., Faili, H. ve Shakery, A. (2019). LICD: A language-independent approach for aspect category detection. L. Azzopardi, B. Stein, N. Fuhr, P. Mayr, C. Hauff, ve D. Hiemstra (Ed.), Advances in information retrieval içinde (s. 575-589). Springer International Publishing.
dc.citation Giannakopoulos, A., Musat, C., Hossmann, A. ve Baeriswyl, M. (2017). Unsupervised Aspect Term Extraction with B-LSTM & CRF using Automatically Labelled Datasets. Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (s. 180-188). Copenhagen, Denmark.
dc.citation Grave, E., Bojanowski, P., Gupta, P., Joulin, A ve T. Mikolov (2018). Learning word vectors for 157 languages. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (s. 3483-3487). Miyazaki, Japan.
dc.citation He, R., Lee, W. S., Ng, H. T. ve Dahlmeier, D. (2017). An Unsupervised Neural Attention Model for Aspect Extraction. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics-Volume 1 (s. 388-397). Vancouver, Canada.
dc.citation Hercig, T., Brychcín, T., Svoboda, L., Konkol, M., Steinberger, J., Hercig, T., Brychcín, T., Svoboda, L., Konkol, M. ve Steinberger, J. (2016). Unsupervised methods to improve aspect-based sentiment analysis in Czech. Computación y Sistemas, 20(3), 365-375.
dc.citation Kama, B., Ozturk, M., Karagoz, P., Toroslu, I. H. ve Ozay, O. (2016). A web search enhanced feature extraction method for aspect-based sentiment analysis for Turkish informal texts. S. Madria ve T. Hara (Ed.), Big data analytics and knowledge discovery içinde (s. 225-238). Springer International Publishing.
dc.citation Kim, K.-S., Yoo-Lee, E. ve Joanna Sin, S.-C. (2011). Social media as information source: Undergraduates’ use and evaluation behavior. Asis&t, 48(1), 1-3.
dc.citation Köksal, A. (2022). Turkish Pre-trained Word2Vec Model. https://github.com/akoksal/Turkish-Word2Vec adresinden 19 Ekim 2022 tarihinde alınmıştır.
dc.citation Lee, T. Y. ve Bradlow, E. T. (2011). Automated marketing research using online customer reviews. Journal of Marketing Research, 48(5), 881-894.
dc.citation Li, K., Chen, C., Quan, X., Ling, Q. ve Song, Y. (2020). conditional augmentation for aspect term extraction via masked sequence-to-sequence generation. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (s. 7056-7066). World Wide Online.
dc.citation Li, X. ve Lam, W. (2017). Deep multi-task learning for aspect term extraction with memory interaction. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (s. 2886-2892). Copenhagen, Denmark.
dc.citation Li, X., Bing, L., Li, P., Lam, W. ve Yang, Z. (2018). Aspect term extraction with history attention and selective transformation. ArXiv:1805.00760, 4194-4200.
dc.citation Liao, M., Li, J., Zhang, H., Wang, L., Wu, X. ve Wong, K.-F. (2019). Coupling global and local context for unsupervised aspect extraction. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (s. 4579-4589). Hong Kong, China.
dc.citation Liu, P., Joty, S. ve Meng, H. (2015). Fine-grained opinion mining with recurrent neural networks and word embeddings. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (s. 1433-1443). Lisbon, Portugal.
dc.citation Ma, D., Li, S., Wu, F., Xie, X. ve Wang, H. (2019). Exploring sequence-to-sequence learning in aspect term extraction. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (s. 3538-3547). Florence, Italy.
dc.citation Mensah, S., Sun, K. ve Aletras, N. (2021). An empirical study on leveraging position embeddings for target-oriented opinion words extraction. arXiv:2109.01238, 9174-9179.
dc.citation Movahedi, S., Ghadery, E., Faili, H. ve Shakery, A. (2019). Aspect category detection via topic-attention network, arXiv:1901.01183, 1-9.
dc.citation Omisakin, O. M., Bandara, C. ve Kularatne, I. (2020). Designing a customer feedback service channel through AI to improve customer satisfaction in the supermarket industry. Journal of Information & Knowledge Management (JIKM), 19(03), 1-34.
dc.citation Ozyurt, B. ve Akcayol, M. A. (2021). A new topic modeling based approach for aspect extraction in aspect based sentiment analysis: SS-LDA. Expert Systems with Applications, 168, 114231.
dc.citation Pang, B., Lee, L. ve Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (s. 79-86). Philadelphia, PA, USA.
dc.citation Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., AL-Smadi, M., Al-Ayyoub, M., Zhao, Y., Qin, B., De Clercq, O., Hoste, V., Apidianaki, M., Tannier, X., Loukachevitch, N., Kotelnikov, E., Bel, N., Jiménez-Zafra, S. M. ve Eryiğit, G. (2016). SemEval-2016 task 5: Aspect based sentiment analysis. Proceedings of the 10th International Workshop on Semantic Evaluation (s. 19-30). San Diego, CA, USA.
dc.citation Pontiki, M., Galanis, D., Pavlopoulos, J., Papageorgiou, H., Androutsopoulos, I. ve Manandhar, S. (2014). SemEval-2014 task 4: Aspect based sentiment analysis. Proceedings of the 8th International Workshop on Semantic Evaluation (s. 27-35). Dublin, Ireland.
dc.citation Salur, M. U. ve Aydin, İ. (2021). An annotated Turkish aspect based sentiment analysis corpus for smart tourism. Proceedings of Innovations in Intelligent Systems and Applications Conference (s. 1-6). Elazig, Turkey.
dc.citation Salur, M. U., Aydın, İ. ve Jamous, M. (2022). An ensemble approach for aspect term extraction in Turkish texts. Pamukkale University Journal of Engineering Sciences, 28(5), 769-776.
dc.citation Schouten, K. ve Frasincar, F. (2016). Survey on aspect-level sentiment analysis. IEEE Transactions on Knowledge and Data Engineering, 28(3), 813-830.
dc.citation SemEval (2016). Task 5: Aspect-Based Sentiment Analysis. https://alt.qcri.org/semeval2016/task5/ adresinden 17 Kasım 2022 tarihinde alınmıştır
dc.citation Shi, T., Li, L., Wang, P. ve Reddy, C. K. (2020). A simple and effective self-supervised contrastive learning framework for aspect detection, arXiv:2009.09107, 1-13.
dc.citation Tulkens, S. ve van Cranenburgh, A. (2020). Embarrassingly simple unsupervised aspect extraction. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (s. 3182-3187. World Wide Online.
dc.citation Veyseh, A. P. B., Nouri, N., Dernoncourt, F., Dou, D. ve Nguyen, T. H. (2020). Introducing syntactic structures into target opinion word extraction with deep learning, arXiv:2010.13378, 8947-8956.
dc.citation Wang, W., Pan, S. J., Dahlmeier, D. ve Xiao, X. (2017). Coupled multi-layer attentions for co-extraction of aspect and opinion terms. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1), 1-7. San Francisco, CA, USA.
dc.citation Winatmoko, Y. A., Septiandri, A. A. ve Sutiono, A. P. (2020). Aspect and Opinion Term Extraction for Hotel Reviews using Transfer Learning and Auxiliary Labels, arXiv:1909.11879, 1-5.
dc.citation Wu, M., Wang, W. ve Pan, S. J. (2020). Deep weighted maxsat for aspect-based opinion extraction. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (s. 5618-5628). World Wide Online.
dc.citation Xu, H., Liu, B., Shu, L. ve Yu, P. S. (2018). Double embeddings and CNN-based sequence labeling for aspect extraction. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics-Volume 2 (s. 592-598). Melbourne, Australia.
dc.citation Yang, Y., Li, K., Quan, X., Shen, W. ve Su, Q. (2020). Constituency lattice encoding for aspect term extraction. Proceedings of the 28th International Conference on Computational Linguistics, (s. 844-855). Barcelona, Spain (Online).
dc.citation Yin, Y., Wei, F., Dong, L., Xu, K., Zhang, M. ve Zhou, M. (2016). Unsupervised word and dependency path embeddings for aspect term extraction. Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (s. 2979-2985). New York, USA.
dc.citation Yoldaş, İ. N. (2021). Türkçe metinlerde duygu analizi: sözlük tabanlı yaklaşım ve insanların tepkilerinin karşılaştırılması. Eskişehir Türk Dünyası Uygulama ve Araştırma Merkezi Bilişim Dergisi, 2(1), 1-6.
dc.citation Yu, J., Jiang, J. ve Xia, R. (2019). Global inference for aspect and opinion terms co-extraction based on multi-task neural networks. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(1), 168-177.
dc.citation Zhang, W., Li, X., Deng, Y., Bing, L. ve Lam, W. (2022). A survey on aspect-based sentiment analysis: Tasks, methods, and challenges, arXiv:2203.01054, 1-21.
dc.citation Zhou, X., Wan, X. ve Xiao, J. (2015). Representation learning for aspect category detection in online reviews. Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (s. 417-423). Austin, TX, USA.


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account