1,720,954 research outputs found
Sosyal medya mesajlarında müşteri memnuniyetinin fuzzy sentiment analizi ile ölçülmesi
No full textSOSYAL MEDYA MESAJLARINDA MÜŞTERİ MEMNUNİYETİNİN FUZZY SENTİMENT ANALİZİ İLE ÖLÇÜLMESİ zeti: Bu tez çerçevesinde, Destek Vektör Makineleri (Support Vector Machine) (SVM), Multimomial Naif Bayes (MNB), K En yakın Komşu (KNN),Fuzzy K En Yakın Komşular (Fuzzy K Nearest Neighbors (FNN)), Fuzzy – Kaba K En Yakın Komşular (Fuzzy-Rough K Nearest Neighbors(FRNN)), Fuzzy Sahiplik En Yakın Komşular (Fuzzy Ownership Nearest Neighbors (FRNN-O)), Fuzzy Kaba EnYakın Komşular- Fuzzy Kaba Kümeler (FRNN-FRS), Fuzzy Hibrit SVM MNB, Fuzzy Hibrit SVM KNN, Fuzzy Hibrit MNB KNN ve Fuzzy Hibrit SVM MNB(FSM) sınıflandırıcıları kullanılarak Fuzzy Sentiment Analizi (FSA) gerçekleştirilmektedir. Tez, işletmelerin sürdürülebilirliklerini sağlamak için, müşteri memnuniyetinin ve sadakatinin sağlanması amacına hizmet edecek, bir katkı sunmayı amaçlamaktadır. İletişim çağında değişen ve ana akım medyadan daha etkili hale gelen en güncel ve özgür haber alma kanalı olan Sosyal medyadaki mesajlara, fuzzy sentiment analizi uygulayarak, bu mesajların, müşterilerin hangi konudaki memnuniyetsizliklerini içerdiğini tespit etmek, bu çalışmanın temel hedefidir. Bunun için öncelikle müşteri memnuniyeti kavramı üzerine bir araştırma yapıldı ve müşteri memnuniyetini / memnuniyetsizliğini oluşturan temel etkenler 5 sınıfa ayrıldı. Sonrasında şikayetvar.com sitesinden alınan 2567 adet mesaj içeriğinin, 5 şikayet sınıfından en uygun olanına atanmasıyla, öğrenme veri kümesi oluşturuldu. Daha sonra, FSA uygulanarak, bu veri kümesi otomatik olarak müşteri memnuniyeti sınıflarına ayrılması denendi ve sonuçların performansı Sentiment Analizi sonuçlarıyla karşılaştırıldı. Fuzzy Sentiment Analizi, Veri Madenciliği, Fuzzy Sınıflandırıcılar, Müşteri Memnuniyeti, Kaba Kümeler MEASURING CUSTOMER SATISFACTION VIA FUZZY SENTIMENT ANALYSIS ON SOCIAL MEDIA MESSAGESfor PhD Dissertation: In this thesis we have used Support Vector Machine(SVM), Multinomial Naive Bayes (MNB), K Nearest Neighbor (KNN), Fuzzy KNN(FNN), Fuzzy Rough K Nearest Neighbors(FRNN), Fuzzy Ownership KNN(FRNN-O), Fuzzy Rough NN – Fuzzy Rouh Set (FRNN-FRS), Fuzzy Hybrit SVM KNN Fuzzy Hybrit MNB KNN, Fuzzy Hybrite SVM MNB KNN and Fuzzy Hybrite SVM MNB (FSM) classifiers for implementing FSA. The main aim of this dissertation is contributing about Providing the customer satisfaction and loyalty for brands in order to guarantee their sustainability. In other words the main target of this disertation is applying fuzzy sentiment analysis on changing and challenging modern new intelligence channel Social Media Messages to detect the type of customer dissatisfaction. Fort his aim firstly the concept of customer satisfaction / dissatisfaction has been researched. After this, the factors which causes customer satisfaction / dissatisfaction, divided into 5 classes. Subsequently 2567 of şikayetvar.com messages (The complaints of customers about product / service is in the content of this messages) and coded them into 5 classes manually. After this we implement the FSA and classify the messages into classes automatically with FSA. Eventually we compare the FSA Performance with Sentiment Analysis’s results. Fuzzy Sentiment Analysis, Data Mining, Fuzzy Classifiers, Customer Satisfaction, Rough Set
Comparing Turkish Universities Entrepreneurship and Innovativeness Index's Rankings with Sentiment Analysis Results on Social Media
No full textAbstractIn this article we have compared the rankings of Turkish Universities obtained by The Scientific And Technological Research Council of Turkey's (TUBITAK) Entrepreneur and Innovative University Index (EIUI) with rankings obtained by Sentiment Analysis(SA) of the related university's students or graduate student's social media messages. SA is a method for automatically mining the attitude of the author (or more generally the source) about a thought, behaviour, service or product. For this case, we have conducted SA in the context of Entrepreneurship and Innovativeness. We used random related university's official twitter account's followers to form a database for user names. Selection of followers and number of followers for university was made randomly. We have used 13.007 tweets that contain “entrepreneur” keyword and 14.579 tweets that contain “Innovation” keyword to identify the relevant class and #OezgecanAslan and #SevgiNeydi trend topic's tweets for irrelevant class and with this way we generate a lexicon about entrepreneurship and innovation for SA. In this generation phase we have used Support Vector Machines and Naive Bayes Classifier data mining algorithms. We have performed SA on the approximately 1.353.803 tweets of 57.321 followers of 50 universities of interested and we obtain a new ranking of these. Finally we have conducted statistical tests for compatibility of these two university rankings
A business analysis on the relationship of sustainability score and financial structure
Get PDFIn this business analysis, the complex interplay between the sustainability scores and the financial structures of modern companies is examined in depth. As a case, one of the largest in Turkey, Koç Holding is selected. Koç Holding exports a wide range of products to the EU countries. The study aims to uncover the key drivers and inhibitors that shape this relationship based on a synthesis of academic literature and empirical research. In this study, text mining was performed on a total of 250 sustainability reports as of July 2020. In this way, the scores were calculated for each of the nine headings. The results were interpreted through the calculation of the regressive relationship between these scores and annual financial performance, revealing the increase in the institution's sensitivity to sustainable development over the years. © 2024, IGI Global. All rights reserved
Comparing Turkish Universities Entrepreneurship and Innovativeness Index's Rankings with Sentiment Analysis Results on Social Media
No full textIn this article we have compared the rankings of Turkish Universities obtained by The Scientific And Technological Research Council of Turkey's (TUBITAK) Entrepreneur and Innovative University Index (EIUI) with rankings obtained by Sentiment Analysis(SA) of the related university's students or graduate student's social media messages. SA is a method for automatically mining the attitude of the author (or more generally the source) about a thought, behaviour, service or product. For this case, we have conducted SA in the context of Entrepreneurship and Innovativeness. We used random related university's official twitter account's followers to form a database for user names. Selection of followers and number of followers for university was made randomly. We have used 13.007 tweets that contain entrepreneur keyword and 14.579 tweets that contain Innovation keyword to identify the relevant class and #OezgecanAslan and #SevgiNeydi trend topic's tweets for irrelevant class and with this way we generate a lexicon about entrepreneurship and innovation for SA. In this generation phase we have used Support Vector Machines and Naive Bayes Classifier data mining algorithms. We have performed SA on the approximately 1.353.803 tweets of 57.321 followers of 50 universities of interested and we obtain a new ranking of these. Finally we have conducted statistical tests for compatibility of these two university rankings. (C) 2015 The Authors. Published by Elsevier Ltd
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
