Duygu Analizi ile Kripto Para İşlemlerindeki Dalgalanmaların İncelenmesi

Yıl 2024, ERKEN GÖRÜNÜM, 1 - 1

Uğur Demirel , Handan Çam

https://doi.org/10.2339/politeknik.1518826

Öz

Bu çalışma, sosyal medya platformlarında ve çevrimiçi forumlarda paylaşılan yorumları kullanarak, Türkiye'deki kripto borsalarında listelenen popüler kripto para birimleri hakkındaki kamuoyunun duyarlılığını araştırmaktadır. Araştırma, Türkçe metinlere odaklanan duygu analizi çalışmalarının eksikliklerini gidererek mevcut bilgi birikimini artırmayı amaçlamaktadır. Sosyal medya ve çevrimiçi forumlardan toplanan veriler duygu analizi teknikleriyle incelenmiştir. Toplam 607.592 yorum analiz edildi ve bunların 89.986'sı olumsuz, 72.655'i olumlu ve 444.951'i nötr olarak sınıflandırılmıştır. İkili sınıflandırma için 89.986 negatif ve 72.655 pozitif örnek seçildi ve makine öğrenimi modelleri eğitildi ve 162.641 örnek üzerinde test edildi. Çalışmanın metodolojisi, makine öğrenimi sınıflandırıcıları kullanılarak elde edilen duygu analizi sonuçlarının derinlemesine incelenmesini içermektedir. Bulgular, çeşitli kripto para birimlerinin farklı sosyal medya platformlarında nasıl algılandığını göstermektedir. Örneğin, BTC (Bitcoin) Investing.com ve Telegram'da genel olarak olumsuz algılanırken, ETH (Ethereum) genellikle daha olumsuz görüşler sergilemektedir. Bu sonuçlar, yatırımcıların kripto para birimlerine yönelik algılarını ve piyasa beklentilerini anlamalarına yardımcı olmaktadır. Bu çalışma, sosyal medya duyarlılık analizinin kripto para piyasalarındaki rolünü derinleştirerek gelecekteki araştırmalar için yeni yöntem ve yaklaşımların geliştirilmesine katkıda bulunmaktadır.

Anahtar Kelimeler

Kripto para, Metin madenciliği, Doğal dil işleme, Makine öğrenmesi, Duygu analizi

Investigation of Fluctuations in Cryptocurrency Transactions with Sentiment Analysis

Öz

This study investigates public sentiment about popular cryptocurrencies listed on crypto exchanges in Turkey, using comments shared on social media platforms and online forums. The research seeks to enhance the existing body of knowledge by overcoming the shortcomings of sentiment analysis studies focused on Turkish texts. Data collected from social media and online forums were examined with sentiment analysis techniques. A total of 607,592 comments were analyzed, of which 89,986 were classified as negative, 72,655 as positive, and 444,951 as neutral. For binary classification, 89,986 negative and 72,655 positive examples were selected and machine-learning models were trained and tested on 162,641 examples. The study's methodology includes an in-depth examination of sentiment analysis results obtained using machine learning classifiers. The findings show how various cryptocurrencies are perceived on different social media platforms. For instance, BTC (Bitcoin) is generally perceived negatively on Investing.com and Telegram, while ETH (Ethereum) generally displays more negative views. These results help investors understand their perceptions and market expectations towards cryptocurrencies. This study deepens the role of social media sentiment analysis in cryptocurrency markets, contributing to the development of new methods and approaches for future research.

Anahtar Kelimeler

Text mining, Natural language processing, Machine learning, Sentiment analysis, Cryptocurrency

Kaynakça

• [1] Go A., Huang L., Bhayani R., "Twitter sentiment analysis", Entropy, 17:252, (2009).
• [2] Appel O., Chiclana F., Carter J., Fujita H., "A hybrid approach to sentiment analysis", 2016 IEEE Congress on Evolutionary Computation (CEC), IEEE, 4950–7, (2016).
• [3] Pang B., Lee L., "Opinion mining and sentiment analysis", Foundations and Trends® in Information Retrieval, 2:1–135, (2008).
• [4] Akba F., Uçan A., Sezer E.A., Sever H., "Assessment of feature selection metrics for sentiment analyses: Turkish movie reviews", 8th European Conference on Data Mining, 191:180–4, (2014).
• [5] Catal C., Nangir M., "A sentiment classification model based on multiple classifiers", Applied Soft Computing, 50:135–41, (2017).
• [6] Çoban Ö., Özyer B., Özyer G.T., "Sentiment analysis for Turkish Twitter feeds", 2015 23nd Signal Processing and Communications Applications Conference (SIU), IEEE, 2388–91 (2015).
• [7] www.octoparse.com, "Octoparse", (2024).
• [8] Pang B., Lee L., V"aithyanathan S. Thumbs up? Sentiment classification using machine learning techniques", arXiv Preprint Cs/0205070, (2002).
• [9] Al-Hadhrami S., Al-Fassam N., Benhidour H., "Sentiment analysis of english tweets: A comparative study of supervised and unsupervised approaches", 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS), IEEE, 1–5, (2019).
• [10] Desai R.D., "Sentiment analysis of Twitter data", 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), IEEE, p. 114–7, (2018).
• [11] El Rahman S.A., AlOtaibi F.A., AlShehri W.A., "Sentiment analysis of twitter data", 2019 international conference on computer and information sciences (ICCIS), IEEE; 1–4, (2019).
• [12] Kurniawati I., Pardede H.F., "Hybrid method of information gain and particle swarm optimization for selection of features of SVM-based sentiment analysis", 2018 International Conference on Information Technology Systems and Innovation (ICITSI), IEEE,1–5, (2018).
• [13] Rane A., Kumar A., "Sentiment classification system of Twitter data for US airline service analysis", 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC), IEEE; 1:769–73, (2018).
• [14] Ray P., Chakrabarti A., "A mixed approach of deep learning method and rule-based method to improve aspect level sentiment analysis", Applied Computing and Informatics (2020).
• [15] Kaya M., Fidan G., Toroslu I.H., "Sentiment analysis of Turkish political news", 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology, IEEE; 1:174–80, (2012).
• [16] Nizam H., Akın S.S., "Sosyal medyada makine öğrenmesi ile duygu analizinde dengeli ve dengesiz veri setlerinin performanslarının karşılaştırılması", XIX Türkiye’de İnternet Konferansı, (2014).
• [17] Meral M., Diri B., "Sentiment analysis on Twitter", 2014 22nd Signal Processing and Communications Applications Conference (SIU), IEEE, 690–3, (2014).
• [18] Kaynar O., Görmez Y., Yıldız M., Albayrak A., "Makine öğrenmesi yöntemleri ile Duygu Analizi", International Artificial Intelligence and Data Processing Symposium (IDAP’16), 234: 241 (2016).
• [19] Parlar T., Saraç E., Özel S.A., "Comparison of feature selection methods for sentiment analysis on Turkish Twitter data", 2017 25th Signal Processing and Communications Applications Conference (SIU), IEEE, 1–4, (2017).
• [20] Velioğlu R., Yıldız T., Yıldırım S., "Sentiment analysis using learning approaches over emojis for Turkish tweets", 2018 3rd International Conference on Computer Science and Engineering (UBMK), IEEE, 303–7, (2018).
• [21] Parlar T., Özel S.A., Song F., "QER: a new feature selection method for sentiment analysis", Human-Centric Computing and Information Sciences, 8:1–19, (2018).
• [22] Ciftci B., Apaydin M.S., "A deep learning approach to sentiment analysis in Turkish", 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), IEEE, 1–5, (2018).
• [23] Cliche M., "BB_twtr at SemEval-2017 task 4: Twitter sentiment analysis with CNNs and LSTMs", arXiv Preprint arXiv:170406125, (2017).
• [24] Hassan A., Mahmood A., "Deep learning approach for sentiment analysis of short texts", 2017 3rd international conference on control, automation and robotics (ICCAR), IEEE, 705–10, (2017).
• [25] Kamis S., Goularas D., "Evaluation of deep learning techniques in sentiment analysis from twitter data", 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML), IEEE; 12–7, (2019).
• [26] Demirci G.M., Keskin Ş.R., Doğan G., "Sentiment analysis in Turkish with deep learning", 2019 IEEE international conference on big data (big data), IEEE, 2215–21, (2019).
• [27] Acikalin U.U., Bardak B., Kutlu M., "Turkish sentiment analysis using bert", 2020 28th Signal Processing and Communications Applications Conference (SIU), IEEE, 1–4, (2020).
• [28] Shehu H.A., Tokat S., "A hybrid approach for the sentiment analysis of Turkish Twitter data", The International Conference on Artificial Intelligence and Applied Mathematics in Engineering, Springer, 182–90, (2020).
• [29] Esuli A., Sebastiani F., "Sentiwordnet: A publicly available lexical resource for opinion mining", Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), (2006).
• [30] Baloglu A., Aktas M.S., "An automated framework for mining reviews from blogosphere", International Journal of Advances in Internet Technology, 3:234–44, (2010).
• [31] Bilgin O., Çetinoğlu Ö., Oflazer K., "Building a wordnet for Turkish", Romanian Journal of Information Science and Technology, 7:163–72, (2004).
• [32] Dehkharghani R., Saygin Y., Yanikoglu B., Oflazer K., "SentiTurkNet: a Turkish polarity lexicon for sentiment analysis", Language Resources and Evaluation, 50:667–85, (2016).
• [33] Akgül E.S., Ertano C., Banu D., "Sentiment analysis with Twitter", Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 22:106–10, (2016).
• [34] Öztürk N., Ayvaz S., "Sentiment analysis on Twitter: A text mining approach to the Syrian refugee crisis", Telematics and Informatics, 35:136–47, (2018).
• [35] Yurtalan G., Koyuncu M., Turhan Ç., "A polarity calculation approach for lexicon-based Turkish sentiment analysis", Turkish Journal of Electrical Engineering & Computer Sciences, 27:1325–39, (2019).
• [36] Ohana B., Tierney B., "Sentiment classification of reviews using SentiWordNet", Proceedings of IT&T, 8, (2009).
• [37] Govindarajan M., "Sentiment analysis of movie reviews using hybrid method of naive bayes and genetic algorithm", International Journal of Advanced Computer Research, 3:139, (2013).
• [38] Türkmenoglu C., Tantug A.C., "Sentiment analysis in Turkish media", International Conference on Machine Learning (ICML), (2014).
• [39] Rumelli M., Akkuş D., Kart Ö., Isik Z., "Sentiment analysis in Turkish text with machine learning algorithms", 2019 Innovations in Intelligent Systems and Applications Conference (ASYU), IEEE; 1–5, (2019).
• [40] Uslu A., Tekin S., Aytekin T., "Sentiment analysis in Turkish film comments", 2019 27th Signal Processing and Communications Applications Conference (SIU), IEEE, 1–4, (2019).
• [41] Erşahi̇n B., Aktaş Ö., Kilinc D., Erşahi̇n M., "A hybrid sentiment analysis method for Turkish", Turkish Journal of Electrical Engineering & Computer Sciences, 27:1780–93, (2019).
• [42] Bollen J., Mao H., Zeng X., "Twitter mood predicts the stock market", Journal of Computational Science, 2:1–8, (2011).
• [43] Zhang X., Fuehres H., Gloor P.A., "Predicting stock market indicators through twitter “I hope it is not as bad as I fear”, Procedia-Social and Behavioral Sciences, 26:55–62, (2011).
• [44] Smailović J., Grčar M., Žnidaršič M., Lavrač N., "Sentiment analysis on tweets in a financial domain", 4th Jožef Stefan International Postgraduate School Students Conference, 1:169–75, (2012).
• [45] Kristoufek L., "BitCoin meets Google Trends and Wikipedia: Quantifying the relationship between phenomena of the Internet era", Scientific Reports, 3:1–7, (2013).
• [46] Wang G., Wang T., Wang B., Sambasivan D., Zhang Z., Zheng H., et al. "Crowds on wall street: Extracting value from social investing platforms", arXiv Preprint arXiv:14061137, (2014).
• [47] Kaminski J., "Nowcasting the bitcoin market with twitter signals", arXiv Preprint arXiv:14067577, (2014).
• [48] Hernandez I., Bashir M., Jeon G., Bohr J., "Are Bitcoin Users Less Sociable? An analysis of users’ language and social connections on twitter", International Conference on Human-Computer Interaction, Springer, 26–31, (2014).
• [49] Garcia D., Tessone C.J., Mavrodiev P., Perony N., "The digital traces of bubbles: feedback cycles between socio-economic signals in the Bitcoin economy", Journal of the Royal Society Interface, 11, (2014).
• [50] Garcia D., Schweitzer F., "Social signals and algorithmic trading of Bitcoin", Royal Society Open Science, 2, (2015).
• [51] Colianni S., Rosales S., Signorotti M., "Algorithmic trading of cryptocurrency based on Twitter sentiment analysis", CS229 Project, 1, (2015).
• [52] www.orangedatamining.com/widget-catalog/text-mining/preprocesstext/, "Preprocess Text", (2022).
• [53] www.orangedatamining.com/widget-catalog/text-mining/sentimentanalysis/, "Sentiment Analysis", (2022).
• [54] www.help.ku.edu.tr/ithelp/jupyter, "Jupyter", (2024).
• [55] Çalış K., Gazdağı O., Yıldız O., "Reklam içerikli epostaların metin madenciliği yöntemleri ile otomatik tespiti", Bilişim Teknolojileri Dergisi, 6:1–7, (2013).
• [56] Onan A., "Twitter mesajlari üzerinde makine öğrenmesi yöntemlerine dayali duygu analizi", Yönetim Bilişim Sistemleri Dergisi, 3:1–14, (2017).
• [57] Akpınar H., "Data: veri madenciliği veri analizi", 2. basım. İstanbul: Papatya Yayıncılık Eğitim, (2017).
• [58] Osmanoğlu U.Ö, Atak O.N, Çağlar K., Kayhan H., Can T.C., "Sentiment analysis for distance education course materials: A machine learning approach", Journal of Educational Technology and Online Learning, 3:31–48, (2020).
• [59] Taşcı E., Onan A., "K-en yakın komşu algoritması parametrelerinin sınıflandırma performansı üzerine etkisinin incelenmesi", Akademik Bilişim, 1:4–18, (2016).
• [60] Çelik Ö., Aslan A.F., "Gender prediction from social media comments with artificial intelligence", Sakarya University Journal of Science, 23:1256–64, (2019).
• [61] Han J., Kamber M., Pei J., "Data mining: concepts and techniques", Morgan kaufmann, (2011).
• [62] Özekes S., "Veri madenciliği modelleri ve uygulama alanları", İstanbul Commerce University Journal of Science, 3:3, (2003).
• [63] Coşlu E., "Veri madenciliği", Akademik Bilişim, 23–5, (2013).
• [64] Soydaş S.S., Çam H., "Predicting Financial Failure in Companies by Employing Machine Learning Methods", International Journal of Social Science Research and Review, 7:111–25, (2024).
• [65] Medhat W., Hassan A., Korashy H., "Sentiment analysis algorithms and applications: A survey", Ain Shams Engineering Journal, 5:1093–113, (2014).
• [66] Si S., Zhang H., Keerthi S.S., Mahajan D., Dhillon I.S., Hsieh C-J., "Gradient boosted decision trees for high dimensional sparse output", International conference on machine learning, PMLR, 3182–90, (2017).
• [67] He Z., Lin D., Lau T., Wu M., "Gradient boosting machine: a survey", arXiv Preprint arXiv:190806951, (2019).
• [68] Hang H., Huang T., Cai Y., Yang H., Lin Z., "Gradient Boosted Binary Histogram Ensemble for Large-scale Regression", (2021).
• [69] Friedman J.H., "Greedy function approximation: a gradient boosting machine", Annals of Statistics, 1189–232, (2001).
• [70] Hamzaçebi C., "Yapay sinir ağları: tahmin amaçlı kullanımı MATLAB ve Neurosolutions uygulamalı", Ekin Basım Yayın Dağıtım, (2011).
• [71] Alpaydin E., "Introduction to machine learning", Cambridge, Mass., MIT Press, (2010).
• [72] Öztemel E., "Yapay sinir ağlari", PapatyaYayincilik, Istanbul, (2012).
• [73] Sokolova M., Lapalme G., "A systematic analysis of performance measures for classification tasks", Information Processing & Management, 45:427–37, (2009).
• [74] Corbet S., Lucey B., Urquhart A., Yarovaya L., "Cryptocurrencies as a financial asset: A systematic analysis", International Review of Financial Analysis, 62:182–99, (2019).
• [75] Feng W., Wang Y., Zhang Z., "Informed trading in the Bitcoin market", Finance Research Letters, 26:63–70, (2018).
• [76] Erdinç U., Bursa N., "Covıd-19 Pandemi Sürecinde Twitter Yorumları İle Altcoın Kripto Para Piyasası Arasındaki Nedenselliğin Duygu Analizi İle İncelenmesi: Ripple Örneği", Yönetim ve Ekonomi Araştırmaları Dergisi, 19:362–81, (2021).
• [77] Kaplan C., Aslan C., Bulbul A., "Cryptocurrency Word-of-Mouth Analysis via Twitter", ResearchGate, (2018).
• [78] Köksal B., Erdem G., Türkeli C., Öztürk Z.K., "Twitter’da Duygu Analizi Yöntemi Kullanılarak Bitcoin Değer Tahminlemesi", Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 9:280–97, (2021).