Yazarlar
Yayınlar
- MakaleAçık Erişim2026Scopus SJRQ2Aspect-Based Sentiment Analysis on Social Media Comments (Twitter) : The Attributes of Service Robots in the Hotel and Restaurant Industry
Acar, Ayşegül; Türten, Burak; Diker, Ersin
Service robots are becoming more prevalent in the service industry, yet the impact they have on customer experiences is not well-documented. This study identified consumer emotions toward service robots in hotels and restaurants, focusing on how specific attributes of these robots affect consumer emotions. Furthermore, it explored which countries generate the most comments on these service robot attributes and the nature of consumer emotions within these regions. Utilizing sentiment analysis, the study examined 52,513 English-language tweets about hotel and restaurant service robots. Additionally, logistic regression analysis helped quantify the impact of robot attributes–categorized as physical, functional, and relational–on different classes of emotions. The findings reveal that customers of restaurants and hotels were most influenced by the physical and relational attributes of service robots, respectively, with functional attributes having the least impact. The logistic regression analysis offered significant insights into how service robot attributes influence consumer experiences in hotels and restaurants.
AtıfScopus5WoS4OpenAlex5
İncele - MakaleAçık Erişim2025Investigation of Fluctuations in Cryptocurrency Transactions with Sentiment Analysis
Demírel, Ugur; Çam, Handan
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.
AtıfWoS1OpenAlex3
İncele - Kitap BölümüYalnız künye2025Sentiment analysis of twitter data for US airlines' finance
Cam, Handan; Demirel, Ugur
The airline industry significantly promotes cultural, social, and financial globalization by facilitating connections between nations and individuals. Airline finance encompasses the intricate aspects of managing the economic, operational, and strategic elements of airline corporations on a global scale. In this industry, it is necessary to address various factors, including revenue management, risk management, cost control, and market competition. The interaction of these factors in the global aviation sector influences the financial situation of airlines, requiring strategic planning, flexibility, and a complete understanding of market dynamics. Sentiment analysis in aviation finance uses text and data mining techniques to examine emotional elements derived from social networks, consumer feedback, and news. This facilitates understanding consumer preferences, new trends, investment opportunities, risks, and marketing strategies. Sentiment analysis also helps manage brand reputation by monitoring sentiments expressed by passengers and the general public, allowing proactive measures to maintain a positive reputation. Airline companies rely on conventional customer feedback forms, which can be extremely laborious and timeconsuming. Twitter data is valuable for collecting consumer feedback tweets and conducting sentiment analysis. In this paper, we work on a dataset comprising tweets from the top major US airlines and perform a sentiment analysis in airline finance that can be used more efficiently and effectively in decision-making processes. This would allow airlines to adopt a more knowledgeable, targeted, and competitive strategy by understanding and assessing emotional context.
- MakaleAçık Erişim2024Scopus SJRQ1Sentiment analysis of financial Twitter posts on Twitter with the machine learning classifiers
Cam, Handan; Cam, Alper Veli; Demirel, Ugur; Ahmed, Sana
This paper presents a sentiment analysis combining the lexicon-based and machine learning (ML)-based approaches in Turkish to investigate the public mood for the prediction of stock market behavior in BIST30, Borsa Istanbul. Our main motivation behind this study is to apply sentiment analysis to financial-related tweets in Turkish. We import 17189 tweets posted as "#Borsaistanbul, #Bist, #Bist30, #Bist100″ on Twitter between November 7, 2022, and November 15, 2022, via a MAXQDA 2020, a qualitative data analysis program. For the lexicon-based side, we use a multilingual sentiment offered by the Orange program to label the polarities of the 17189 samples as positive, negative, and neutral labels. Neutral labels are discarded for the machine learning experiments. For the machine learning side, we select 9076 data as positive and negative to implement the classification problem with six different supervised machine learning classifiers conducted in Python 3.6 with the sklearn library. In experiments, 80 % of the selected data is used for the training phase and the rest is used for the testing and validation phase. Results of the experiments show that the Support Vector Machine and Multilayer Perceptron classifier perform better than other classifiers with 0.89 and 0.88 accuracy and AUC values of 0.8729 and 0.8647 respectively. Other classifiers obtain approximately a 78,5 % accuracy rate. It is possible to increase sentiment analysis accuracy with parameter optimization on a larger, cleaner, and more balanced dataset by changing the pre-processing steps. This work can be expanded in the future to develop better sentiment analysis using deep learning approaches.
AtıfScopus51WoS19OpenAlex54
İncele - Doktora TeziAçık Erişim2023Dijital bankacılık uygulamalarına ilişkin müşteri yorumlarının metin madenciliği yöntemleri ile incelenmesi
Burcu Sayın Okatan
Son dönemlerde dijital bankacılık finans sektörünün odak noktası haline gelmiştir. Bankaların sektörde yer alması ve gelişimi dijitalleşme konusundaki entegrasyonu ile pararlellik göstermektedir. Dijital yaşamın en önemli rahatlıklarından biri her an kolay ulaşım sağlanan sanal hizmetlerdir. Dijital bankacılık da bu anlamda en çok kullanılan çevrimiçi finans hizmetlerindendir. Buna paralel olarak bu tez çalışmasının amacı; banka müşterilerinin bankanın dijital bankacılığı ile alakalı yapmış oldukları yorumlardan oluşan veri tabanını kullanarak metin madenciliği yöntemleri ile analiz etmektir. Analiz sonuçlarından faydalanarak ülkemizde bulunan bankaların dijital bankacılıkta müşterilerin taleplerini ne oranda karşıladığını tespit etmek ve bu yönde öneriler geliştirmektir. Çalışmanın anakütlesini, Türkiye Bankalar Birliği verileri ışığında en çok kullanılan 3 adet devlet bankası 10 adet özel banka olmak üzere toplamda 13 adet bankaya ait dijital bankacılık verileri oluşturmaktadır. 2020 yılının Ocak Ayı ile 2022 yılının Ağustos Ayı arası tarih aralığı olarak belirlenmiştir. Toplamda 1.200.000-1.250.000 arasında ham veri ilgili sosyal medya platformlarından elde edilmiştir. Veriye uygulanan ön işlemler sonucunda toplam veri 580.000 civarında belirlenmiştir. İncelenen bankaların tek tek kelime yoğunlukları hakkında analizler uygulanmış, wordcloud veri görselleri oluşturulmuş ve duygu analizi sonuçları ile elde edilen bulgular her banka için ayrı ayrı yorumlanmıştır. Çalışmanın sonucunda, banka müşterileri tarafından en çok; kullanışlılık, kolaylık, hizmet ücretleri, özellikle mobil bankacılıkta uygulamanın rahat erişimli ve hızlı olmasından söz edilmiştir. Bu anlamda dijital bankacılık hizmetlerinde, özel bankalar ile kamu bankaları arasında, aşırı farklar olmasa da ayrımın genellikle kullanıma dayalı farklara dayalı olduğu tespit edilmiştir. Bulgular sonucunda bankalara dijital bankacılık sürecinde kaliteli hizmet sunumu ve müşteri memnuniyeti kapsamında farklı önerilerde bulunulmuştur.