Fatma Gülşah Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fatma Gülşah Tan has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Asım Sinan Yüksel
Süleyman Demirel University
7 shared publications - Muhammed Abdulhamid Karabiyik
Department of Computer Technologies, Nigde Omer Halisdemir University, Nide, Trkiye
3 shared publications
Latest Publications
- Open Access
- 25 August 2026
- Published by SDU Journal of Natural and Applied Sciences in SDÜ Fen Bilimleri Enstitüsü Dergisi
- Vol. 30 (2) , 466-480
Imb-LLMClass: A Large Language Model-Based Framework for Imbalanced Text Classification
Class imbalance constitutes a significant challenge in text classification tasks, particularly due to the insufficient representation of minority-class instances. Traditional machine learning methods trained on imbalanced datasets tend to exhibit a bias toward majority classes, thereby limiting their ability to accurately classify minority-class samples. To address this issue, this study proposes a classification framework, termed Imb-LLMClass, to investigate the effectiveness of large language model-based classification approaches for imbalanced text data. Experimental results demonstrate that the proposed Imb-LLMClass framework achieved the highest performance among the compared methods when evaluated based on the average of three experimental runs, attaining a Macro F1-Score of 0.878 and a Balanced Accuracy of 0.870 across three datasets. Furthermore, the increase in the average minority-class recall to 0.834 indicates that the proposed approach not only improves overall classification performance but also enhances the learning of underrepresented classes. These findings indicate that, in imbalanced text classification tasks, evaluating large language models solely based on overall performance metrics may be insufficient and that their ability to effectively represent minority classes should also be taken into consideration.
- 25 August 2026
- Published by SDU Journal of Natural and Applied Sciences in SDÜ Fen Bilimleri Enstitüsü Dergisi
- Vol. 30 (2) , 466-480
Open AccessImb-LLMClass: A Large Language Model-Based Framework for Imbalanced Text Classification
Class imbalance constitutes a significant challenge in text classification tasks, particularly due to the insufficient representation of minority-class instances. Traditional machine learning methods trained on imbalanced datasets tend to exhibit a bias toward majority classes, thereby limiting their ability to accurately classify minority-class samples. To address this issue, this study proposes a classification framework, termed Imb-LLMClass, to investigate the effectiveness of large language model-based classification approaches for imbalanced text data. Experimental results demonstrate that the proposed Imb-LLMClass framework achieved the highest performance among the compared methods when evaluated based on the average of three experimental runs, attaining a Macro F1-Score of 0.878 and a Balanced Accuracy of 0.870 across three datasets. Furthermore, the increase in the average minority-class recall to 0.834 indicates that the proposed approach not only improves overall classification performance but also enhances the learning of underrepresented classes. These findings indicate that, in imbalanced text classification tasks, evaluating large language models solely based on overall performance metrics may be insufficient and that their ability to effectively represent minority classes should also be taken into consideration.
- Open Access
- 4 June 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3939
Architectural blueprinting for pattern-driven refactoring: a multi-agent framework with bounded recovery
Refactoring by design patterns is difficult to do in practice as it requires inferring and enforcing architectural intent across multiple abstractions while maintaining correct behavior. Managing these abstraction layers has been a challenge for automated approaches to address in a controlled and unified way. Prior work addresses smell detection, pattern recommendation, and refactoring largely in isolation, lacking an end-to-end workflow that integrates role-level planning with systematic validation. This article presents PatternForge, a multi-agent large language model framework for architecture-level refactoring that transforms code smells into canonical design-pattern implementations through an explicit, staged reasoning and validation pipeline. PatternForge decomposes refactoring into specialized agents responsible for architectural diagnosis, pattern selection, role-level planning, structural transformation, and validation. By explicitly constraining architectural intent prior to code generation and coupling transformation with bounded validation and recovery, the framework enables more controlled and interpretable refactoring than metric-driven or single-agent approaches. Quantitative results are reported on 72 controlled instances; four additional real-world cases are used solely for qualitative analysis. We evaluate PatternForge using a controlled capability study on a curated benchmark covering six representative code smells—Long Method, God Class, Feature Envy, Switch Statement, Data Class, and Duplicated Code—across three complexity levels and two statically typed languages, Java and C#. We report compilation success ratio and test-pass ratio conditional on successful compilation separately; instances that fail compilation are excluded from test execution and are counted only in compilation statistics. Traditional structural metrics are reported to characterize architectural trade-offs rather than being treated as direct optimization objectives. PatternForge compiled all but one of the 72 refactored instances. Architecturally relevant results were rated as High, Medium, and Low according to Pattern Conformance Level. The non-compiled instance was due to incomplete pattern implementation rather than behavioral failure. Across the benchmark, PatternForge preserves observed program behaviors under the provided test suites, achieving high compilation success ratios while producing refactorings with a higher Pattern Conformance Level than ablated variants and single-agent baselines. Ablation analysis demonstrates that explicit architectural planning primarily determines pattern conformance level, whereas systematic validation is essential for behavioral reliability, highlighting their complementary roles in architecture-level refactoring. These results suggest that multi-agent decomposition with plan-grounded validation provides a practical and controllable foundation for pattern-driven refactoring in statically typed software systems.
- 4 June 2026
- Published by PeerJ in PeerJ Computer Science
- Vol. 12, e3939
Open AccessArchitectural blueprinting for pattern-driven refactoring: a multi-agent framework with bounded recovery
Refactoring by design patterns is difficult to do in practice as it requires inferring and enforcing architectural intent across multiple abstractions while maintaining correct behavior. Managing these abstraction layers has been a challenge for automated approaches to address in a controlled and unified way. Prior work addresses smell detection, pattern recommendation, and refactoring largely in isolation, lacking an end-to-end workflow that integrates role-level planning with systematic validation. This article presents PatternForge, a multi-agent large language model framework for architecture-level refactoring that transforms code smells into canonical design-pattern implementations through an explicit, staged reasoning and validation pipeline. PatternForge decomposes refactoring into specialized agents responsible for architectural diagnosis, pattern selection, role-level planning, structural transformation, and validation. By explicitly constraining architectural intent prior to code generation and coupling transformation with bounded validation and recovery, the framework enables more controlled and interpretable refactoring than metric-driven or single-agent approaches. Quantitative results are reported on 72 controlled instances; four additional real-world cases are used solely for qualitative analysis. We evaluate PatternForge using a controlled capability study on a curated benchmark covering six representative code smells—Long Method, God Class, Feature Envy, Switch Statement, Data Class, and Duplicated Code—across three complexity levels and two statically typed languages, Java and C#. We report compilation success ratio and test-pass ratio conditional on successful compilation separately; instances that fail compilation are excluded from test execution and are counted only in compilation statistics. Traditional structural metrics are reported to characterize architectural trade-offs rather than being treated as direct optimization objectives. PatternForge compiled all but one of the 72 refactored instances. Architecturally relevant results were rated as High, Medium, and Low according to Pattern Conformance Level. The non-compiled instance was due to incomplete pattern implementation rather than behavioral failure. Across the benchmark, PatternForge preserves observed program behaviors under the provided test suites, achieving high compilation success ratios while producing refactorings with a higher Pattern Conformance Level than ablated variants and single-agent baselines. Ablation analysis demonstrates that explicit architectural planning primarily determines pattern conformance level, whereas systematic validation is essential for behavioral reliability, highlighting their complementary roles in architecture-level refactoring. These results suggest that multi-agent decomposition with plan-grounded validation provides a practical and controllable foundation for pattern-driven refactoring in statically typed software systems.
- Open Access
- 31 December 2024
- Published by Izmir Akademi Dernegi in Journal of Metaverse
- Vol. 4 (2) , 157-164
Application of Prompt Engineering Techniques to Optimize Information Retrieval in the Metaverse
Prompt engineering techniques are instructions that enable large language models (LLMs) to solve real-world problems more effectively. These techniques enhance the capabilities of LLMs to generate accurate and efficient responses. Our study examines the challenge of acquiring comprehensive and efficient information in the metaverse through the application of various prompt engineering techniques. The main objective is to improve the accuracy and effectiveness of metaverse-related responses by leveraging LLM capabilities. In this study, 100 questions were generated using GPT, GEMINI, QWEN, and MISTRAL language models focusing on the metaverse. Our experiments indicated that responses often included unrelated information, highlighting the need for prompt engineering techniques. We applied knowledge-based, rule-based, few-shot, and template-based prompt engineering techniques to refine the responses. The performance of GPT, GEMINI, QWEN, and MISTRAL models were evaluated based on criteria including accuracy, timeliness, comprehensiveness, and consistency. Our findings reveal that prompt engineering techniques significantly enhance the efficacy of LLMs in providing improved information retrieval and response generation, aiding users in efficiently acquiring information in complex environments like the metaverse.
- 31 December 2024
- Published by Izmir Akademi Dernegi in Journal of Metaverse
- Vol. 4 (2) , 157-164
Open AccessApplication of Prompt Engineering Techniques to Optimize Information Retrieval in the Metaverse
Prompt engineering techniques are instructions that enable large language models (LLMs) to solve real-world problems more effectively. These techniques enhance the capabilities of LLMs to generate accurate and efficient responses. Our study examines the challenge of acquiring comprehensive and efficient information in the metaverse through the application of various prompt engineering techniques. The main objective is to improve the accuracy and effectiveness of metaverse-related responses by leveraging LLM capabilities. In this study, 100 questions were generated using GPT, GEMINI, QWEN, and MISTRAL language models focusing on the metaverse. Our experiments indicated that responses often included unrelated information, highlighting the need for prompt engineering techniques. We applied knowledge-based, rule-based, few-shot, and template-based prompt engineering techniques to refine the responses. The performance of GPT, GEMINI, QWEN, and MISTRAL models were evaluated based on criteria including accuracy, timeliness, comprehensiveness, and consistency. Our findings reveal that prompt engineering techniques significantly enhance the efficacy of LLMs in providing improved information retrieval and response generation, aiding users in efficiently acquiring information in complex environments like the metaverse.
- 3 December 2024
- Published by Kahramanmaras Sutcu Imam University Journal of Engineering Sciences in Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi
- Vol. 27 (4) , 1401-1420
İSTEM MÜHENDİSLİĞİNİN BÜYÜK DİL MODELLERİNİN PERFORMANSINDAKİ ROLÜ: ANALİZ VE UYGULAMA ÖRNEKLERİ
İstem mühendisliği, büyük dil modellerinin yeteneklerini artırmak için kritik bir teknik olarak ortaya çıkmıştır. İstem adı verilen talimatlar ile model parametrelerini değiştirmeden ince ayar yapma imkânı sunarak, bu modellerin çeşitli görevlerde üstün performans göstermesini sağlar. Bu çalışmanın temel amacı, büyük dil modeli performansını iyileştirmek, hesaplama maliyetlerini azaltmak ve kullanıcı deneyimini geliştirmek için istem mühendisliğinin nasıl etkili kullanılacağını göstermektir. Çalışmada, farklı uygulama alanlarına göre kategorize edilen ve son teknoloji 15 istem mühendisliği tekniği analiz edilmiştir. Bu teknikler, sıfır atış ve birkaç atış istemlerinden düşünce zinciri ve otomatik düşünce zinciri istemlerine kadar çeşitlilik göstermektedir. Her bir tekniğin avantajları ve dezavantajları detaylı olarak değerlendirilmiş ve performans artışının nasıl sağlandığı örnek senaryolarla gösterilmiştir. Araştırmanın sonuçları, istem mühendisliğinin büyük dil modellerinin çeşitli görev ve uygulamalarda performansını artırmada önemli bir rol oynadığını göstermektedir. Özellikle az verili öğrenme senaryolarında verimliliği artırmak ve önyargı, tutarsızlık gibi zorlukları azaltmak için yenilikçi istem mühendisliği tekniklerinin başarılı performans sergiledikleri görülmüştür. Bu bulgular, araştırmacılar ve uygulayıcılar için yol gösterici bir kaynak olarak hizmet edecek ve büyük dil modellerinin geniş çapta uygulanabilirliğini artıracaktır. Çalışmamız, istem mühendisliğinin daha iyi anlaşılmasına katkı sağlayacak ve gelecekteki araştırmalara ışık tutacaktır.
- 3 December 2024
- Published by Kahramanmaras Sutcu Imam University Journal of Engineering Sciences in Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi
- Vol. 27 (4) , 1401-1420
İSTEM MÜHENDİSLİĞİNİN BÜYÜK DİL MODELLERİNİN PERFORMANSINDAKİ ROLÜ: ANALİZ VE UYGULAMA ÖRNEKLERİ
İstem mühendisliği, büyük dil modellerinin yeteneklerini artırmak için kritik bir teknik olarak ortaya çıkmıştır. İstem adı verilen talimatlar ile model parametrelerini değiştirmeden ince ayar yapma imkânı sunarak, bu modellerin çeşitli görevlerde üstün performans göstermesini sağlar. Bu çalışmanın temel amacı, büyük dil modeli performansını iyileştirmek, hesaplama maliyetlerini azaltmak ve kullanıcı deneyimini geliştirmek için istem mühendisliğinin nasıl etkili kullanılacağını göstermektir. Çalışmada, farklı uygulama alanlarına göre kategorize edilen ve son teknoloji 15 istem mühendisliği tekniği analiz edilmiştir. Bu teknikler, sıfır atış ve birkaç atış istemlerinden düşünce zinciri ve otomatik düşünce zinciri istemlerine kadar çeşitlilik göstermektedir. Her bir tekniğin avantajları ve dezavantajları detaylı olarak değerlendirilmiş ve performans artışının nasıl sağlandığı örnek senaryolarla gösterilmiştir. Araştırmanın sonuçları, istem mühendisliğinin büyük dil modellerinin çeşitli görev ve uygulamalarda performansını artırmada önemli bir rol oynadığını göstermektedir. Özellikle az verili öğrenme senaryolarında verimliliği artırmak ve önyargı, tutarsızlık gibi zorlukları azaltmak için yenilikçi istem mühendisliği tekniklerinin başarılı performans sergiledikleri görülmüştür. Bu bulgular, araştırmacılar ve uygulayıcılar için yol gösterici bir kaynak olarak hizmet edecek ve büyük dil modellerinin geniş çapta uygulanabilirliğini artıracaktır. Çalışmamız, istem mühendisliğinin daha iyi anlaşılmasına katkı sağlayacak ve gelecekteki araştırmalara ışık tutacaktır.
- Open Access
- 2 December 2024
- Published by Afyon Kocatepe Universitesi Fen Ve Muhendislik Bilimleri Dergisi in Afyon Kocatepe University Journal of Sciences and Engineering
- Vol. 24 (6) , 1355-1363
Yapay Zekâ Çağında Duygu Analizi: Büyük Dil Modellerinin Yükselişi ve Klasik Yaklaşımlarla Karşılaştırılması
Duygu analizi, günümüzde hem bireylerin hem de şirketlerin karar alma süreçlerinde önemli bir rol oynayan, farklı veri kaynaklarından elde edilen bilgileri inceleyerek insan duygularını anlamayı sağlayan bir yöntemdir. Duygu analizi klasik makine öğrenmesi yöntemleriyle gerçekleştirildiğinde, metinlerin duygusal içeriğini anlamak için genellikle belirli özelliklerin elle seçilmesini ve öznitelik mühendisliği gerektirir. Bu yöntemler, duygusal ifadelerin karmaşıklığını ve çok katmanlı yapısını tam olarak yakalayamamakta ve genellikle belirli bağlamlarda başarılı olmaktadırlar. Ancak, büyük dil modelleri, derin öğrenme prensiplerine dayanarak, karmaşık dil yapılarını daha etkili bir şekilde öğrenebilirler. Bu modeller, büyük ölçekteki metin verilerini işleyerek genel dil bilgisiyle donanmışlardır. Dolayısıyla, duygu analizi gibi görevlerde kullanıldıklarında, öznitelik mühendisliği gerektirmeden karmaşık duygusal ifadeleri daha doğru bir şekilde çözebilirler. Çalışmamızda, üç farklı veri seti kullanılarak büyük dil modelleri ve klasik yöntemlerin duygu analizindeki performansları karşılaştırılmıştır. Sonuçlar, büyük dil modellerinin klasik yöntemlere kıyasla daha yüksek doğruluk oranları elde ettiğini, duygu analizi alanında gelecekte daha fazla kullanılacağını ve bu alandaki çalışmalara önemli katkılar sağlayacağını göstermektedir.
- 2 December 2024
- Published by Afyon Kocatepe Universitesi Fen Ve Muhendislik Bilimleri Dergisi in Afyon Kocatepe University Journal of Sciences and Engineering
- Vol. 24 (6) , 1355-1363
Open AccessYapay Zekâ Çağında Duygu Analizi: Büyük Dil Modellerinin Yükselişi ve Klasik Yaklaşımlarla Karşılaştırılması
Duygu analizi, günümüzde hem bireylerin hem de şirketlerin karar alma süreçlerinde önemli bir rol oynayan, farklı veri kaynaklarından elde edilen bilgileri inceleyerek insan duygularını anlamayı sağlayan bir yöntemdir. Duygu analizi klasik makine öğrenmesi yöntemleriyle gerçekleştirildiğinde, metinlerin duygusal içeriğini anlamak için genellikle belirli özelliklerin elle seçilmesini ve öznitelik mühendisliği gerektirir. Bu yöntemler, duygusal ifadelerin karmaşıklığını ve çok katmanlı yapısını tam olarak yakalayamamakta ve genellikle belirli bağlamlarda başarılı olmaktadırlar. Ancak, büyük dil modelleri, derin öğrenme prensiplerine dayanarak, karmaşık dil yapılarını daha etkili bir şekilde öğrenebilirler. Bu modeller, büyük ölçekteki metin verilerini işleyerek genel dil bilgisiyle donanmışlardır. Dolayısıyla, duygu analizi gibi görevlerde kullanıldıklarında, öznitelik mühendisliği gerektirmeden karmaşık duygusal ifadeleri daha doğru bir şekilde çözebilirler. Çalışmamızda, üç farklı veri seti kullanılarak büyük dil modelleri ve klasik yöntemlerin duygu analizindeki performansları karşılaştırılmıştır. Sonuçlar, büyük dil modellerinin klasik yöntemlere kıyasla daha yüksek doğruluk oranları elde ettiğini, duygu analizi alanında gelecekte daha fazla kullanılacağını ve bu alandaki çalışmalara önemli katkılar sağlayacağını göstermektedir.
- 24 August 2023
- Published by Wiley in Expert Systems
- Vol. 40 (10)
DeepCens: A deep learning‐based system for real‐time image and video censorship
The popularity of social networks and video‐on‐demand platforms has increased the importance of image and video censorship. These platforms contain various content such as violence, explicit content, drug use and smoking that may be offensive or harmful to certain viewers. As a result, censorship is employed to filter or remove content that is unsuitable for particular audiences such as children and teenagers. However, policies for censoring harmful content in digital environments are either limited or nonexistent. This underscores the need for automated systems that can detect and censor harmful content in real time. To address these challenges, we developed the first of our knowledge systems using deep learning techniques to censor harmful content. We propose two novel, YOLO‐based real‐time censorship algorithms. Our approaches employ a pipeline‐based architecture that parallelizes the operations with subprocesses. In our experiments, the proposed algorithms performed faster and with higher accuracies compared to traditional approaches. Specifically, its content‐based accuracies were 98% for explicit content, 97% for alcohol, 98% for cigarettes and 97% for violence. Our research highlights the importance of developing effective and efficient solutions for censoring harmful content on digital media platforms. Our deep learning‐based system represents a promising approach to this challenge and has the potential to enhance user safety and protect vulnerable groups from harmful and offensive content. Future research will continue to refine and improve such systems to better address the evolving landscape of digital media and the challenges posed by harmful content.
- 24 August 2023
- Published by Wiley in Expert Systems
- Vol. 40 (10)
DeepCens: A deep learning‐based system for real‐time image and video censorship
The popularity of social networks and video‐on‐demand platforms has increased the importance of image and video censorship. These platforms contain various content such as violence, explicit content, drug use and smoking that may be offensive or harmful to certain viewers. As a result, censorship is employed to filter or remove content that is unsuitable for particular audiences such as children and teenagers. However, policies for censoring harmful content in digital environments are either limited or nonexistent. This underscores the need for automated systems that can detect and censor harmful content in real time. To address these challenges, we developed the first of our knowledge systems using deep learning techniques to censor harmful content. We propose two novel, YOLO‐based real‐time censorship algorithms. Our approaches employ a pipeline‐based architecture that parallelizes the operations with subprocesses. In our experiments, the proposed algorithms performed faster and with higher accuracies compared to traditional approaches. Specifically, its content‐based accuracies were 98% for explicit content, 97% for alcohol, 98% for cigarettes and 97% for violence. Our research highlights the importance of developing effective and efficient solutions for censoring harmful content on digital media platforms. Our deep learning‐based system represents a promising approach to this challenge and has the potential to enhance user safety and protect vulnerable groups from harmful and offensive content. Future research will continue to refine and improve such systems to better address the evolving landscape of digital media and the challenges posed by harmful content.
- 11 July 2020
- Published by Springer Nature
- p. 187-194
Estimating Breathing Levels of Asthma Patients with Artificial Intelligence Methods
- 11 July 2020
- Published by Springer Nature
- p. 187-194
Estimating Breathing Levels of Asthma Patients with Artificial Intelligence Methods
- Open Access
- 2 October 2018
- Published by Taylor & Francis in Automatika
- Vol. 59 (3-4) , 261-273
A real-time social network-based knowledge discovery system for decision making
The increasing amount of data in social networks has complicated data processing and interpretation. Therefore, intelligent decision-support mechanisms that have the ability to automatically extract meaning from data and interpret the opinions of people in real time have become inevitable. In this study, an intelligent multilingual decision support system was implemented, and a new algorithm that employs text mining and sentiment analysis techniques was developed to automatically interpret the opinions of social network users about the places they plan to visit. The system can be used as a baseline for sentiment analysis in social networks and can be adapted to build new systems. In this study, we set our main focus on Turkish language and show the applicability of our approach for other languages through the experiments for English language. The dataset required for the implementation of text mining techniques was created based on the venue recommendations shared on Foursquare social media platform. As a result, a contribution was made to the way the social network users make decisions without reading thousands of recommendations. Our results show that the developed system achieves classification accuracy of 84.49% for Turkish and 95% for English. Finally, the most liked or disliked foods/beverages are correctly identified for 107 out of 128 venues.
- 2 October 2018
- Published by Taylor & Francis in Automatika
- Vol. 59 (3-4) , 261-273
Open AccessA real-time social network-based knowledge discovery system for decision making
The increasing amount of data in social networks has complicated data processing and interpretation. Therefore, intelligent decision-support mechanisms that have the ability to automatically extract meaning from data and interpret the opinions of people in real time have become inevitable. In this study, an intelligent multilingual decision support system was implemented, and a new algorithm that employs text mining and sentiment analysis techniques was developed to automatically interpret the opinions of social network users about the places they plan to visit. The system can be used as a baseline for sentiment analysis in social networks and can be adapted to build new systems. In this study, we set our main focus on Turkish language and show the applicability of our approach for other languages through the experiments for English language. The dataset required for the implementation of text mining techniques was created based on the venue recommendations shared on Foursquare social media platform. As a result, a contribution was made to the way the social network users make decisions without reading thousands of recommendations. Our results show that the developed system achieves classification accuracy of 84.49% for Turkish and 95% for English. Finally, the most liked or disliked foods/beverages are correctly identified for 107 out of 128 venues.
- Open Access
- 23 June 2018
- Published by Muhendislik Bilimleri ve Tasarim Dergisi in Mühendislik Bilimleri ve Tasarım Dergisi
- Vol. 6 (2) , 324-333
KNOWLEDGE DISCOVERY IN SOCIAL NETWORKS USING TEXT MINING TECHNIQUES
Al ağların popülerleşmesi ile birlikte sosyal medya ortamlarındaki veri akışı artmıştır. Verinin artması, yapısal olmayan veri miktarını arttırmış, dolayısıyla veriden anlam çıkarabilme yeteneği olan, otomatik olarak duygu analizi yapan karar destek sistemlerinin önemi artmıştır. Bu çalışmada sosyal ağlardan daha yararlı bilgilere ulaşmak, kişilerin bulundukları çevrede gitmeyi planladıkları mekânlar hakkındaki görüşlerini otomatik olarak yorumlamak amacıyla, metin madenciliği ve duygu analizi teknikleri uygulanarak bir karar destek sistemi geliştirilmiştir. Olumlu ve olumsuz görüşler gerçek zamanlı olarak belirlenmekte ve duygu analizleri otomatik bir şekilde yapılmaktadır. Metin madenciliği tekniklerinin uygulanması için gerekli olan veri setleri insanların dünya üzerinde herhangi bir şehirde yemek, içmek, alışveriş yapmak veya ziyaret etmek için mekânları bulmalarını sağlayan Foursquare sosyal paylaşım platformunda bulunan yorumlardan oluşturulmuştur. İngilizce için kullanılan duygu analizi yöntemlerinin Türkçede göstereceği tepkiler incelenmiş ve Türkçeye özel yeni bir yöntem geliştirilerek duygu analizi metotları ile birleştirilmiştir. İkili sınıflandırmada %81,97, üçlü sınıflandırmada ise %84,49 başarı oranı elde edilmiştir.
- 23 June 2018
- Published by Muhendislik Bilimleri ve Tasarim Dergisi in Mühendislik Bilimleri ve Tasarım Dergisi
- Vol. 6 (2) , 324-333
Open AccessKNOWLEDGE DISCOVERY IN SOCIAL NETWORKS USING TEXT MINING TECHNIQUES
Al ağların popülerleşmesi ile birlikte sosyal medya ortamlarındaki veri akışı artmıştır. Verinin artması, yapısal olmayan veri miktarını arttırmış, dolayısıyla veriden anlam çıkarabilme yeteneği olan, otomatik olarak duygu analizi yapan karar destek sistemlerinin önemi artmıştır. Bu çalışmada sosyal ağlardan daha yararlı bilgilere ulaşmak, kişilerin bulundukları çevrede gitmeyi planladıkları mekânlar hakkındaki görüşlerini otomatik olarak yorumlamak amacıyla, metin madenciliği ve duygu analizi teknikleri uygulanarak bir karar destek sistemi geliştirilmiştir. Olumlu ve olumsuz görüşler gerçek zamanlı olarak belirlenmekte ve duygu analizleri otomatik bir şekilde yapılmaktadır. Metin madenciliği tekniklerinin uygulanması için gerekli olan veri setleri insanların dünya üzerinde herhangi bir şehirde yemek, içmek, alışveriş yapmak veya ziyaret etmek için mekânları bulmalarını sağlayan Foursquare sosyal paylaşım platformunda bulunan yorumlardan oluşturulmuştur. İngilizce için kullanılan duygu analizi yöntemlerinin Türkçede göstereceği tepkiler incelenmiş ve Türkçeye özel yeni bir yöntem geliştirilerek duygu analizi metotları ile birleştirilmiştir. İkili sınıflandırmada %81,97, üçlü sınıflandırmada ise %84,49 başarı oranı elde edilmiştir.