Aka Uymaz, Hande
Loading...
Profile URL
Name Variants
Uymaz, Hande Aka
Uymaz, H.A.
Uymaz, H.
Uymaz, H.A.
Uymaz, H.
Job Title
Email Address
hande.aka@ieu.edu.tr
Main Affiliation
05.04. Software Engineering
Status
Current Staff
Website
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Sustainable Development Goals
SDG data is not available
Documents
8
Citations
50
h-index
3
Documents
5
Citations
25
Scholarly Output
11
Articles
4
Views / Downloads
15/30
Supervised MSc Theses
1
Supervised PhD Theses
1
WoS Citation Count
25
Scopus Citation Count
50
WoS h-index
2
Scopus h-index
3
Patents
0
Projects
0
WoS Citations per Publication
2.27
Scopus Citations per Publication
4.55
Open Access Source
3
Supervised Theses
2
| Journal | Count |
|---|---|
| 2017 25th Signal Processing and Communications Applications Conference, SIU 2017 | 1 |
| Communications in Computer and Information Science | 1 |
| Engıneerıng Applıcatıons of Artıfıcıal Intellıgence | 1 |
| Expert Systems With Applications | 1 |
| International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K - Proceedings | 1 |
Current Page: 1 / 2
Scopus Quartile Distribution
Competency Cloud
11 results
Scholarly Output Search Results
Now showing 1 - 10 of 11
Conference Object Citation - Scopus: 1Optimizing High-Dimensional Text Embeddings in Emotion Identification: a Sliding Window Approach(Science and Technology Publications, Lda, 2024) Uymaz, H.A.; Metin, S.K.Natural language processing (NLP) is an interdisciplinary field that enables machines to understand and generate human language. One of the crucial steps in several NLP tasks, such as emotion and sentiment analysis, text similarity, summarization, and classification, is transforming textual data sources into numerical form, a process called vectorization. This process can be grouped into traditional, semantic, and contextual vectorization methods. Despite their advantages, these high-dimensional vectors pose memory and computational challenges. To address these issues, we employed a sliding window technique to partition high-dimensional vectors, aiming not only to enhance computational efficiency but also to detect emotional information within specific vector dimensions. Our experiments utilized emotion lexicon words and emotionally labeled sentences in both English and Turkish. By systematically analyzing the vectors, we identified consistent patterns with emotional clues. Our findings suggest that focusing on specific sub-vectors rather than entire high-dimensional BERT vectors can capture emotional information effectively, without performance loss. With this approach, we examined an increase in pairwise cosine similarity scores within emotion categories when using only sub-vectors. The results highlight the potential of the use of sub-vector techniques, offering insights into the nuanced integration of emotions in language and the applicability of these methods across different languages. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.Conference Object Enhancing Text Embeddings for Emotion Detection: A Study on Dimensionality Reduction and Lexicon Filtering(Springer Science and Business Media Deutschland GmbH, 2026) Uymaz, H.; Kumova Metin, S.Emotion detection in textual data is a crucial task in Natural language processing (NLP), yet standard word embeddings often fail to capture emotional nuances. This study explores an emotion-enrichment approach that refines text representations by integrating emotional information into word embeddings. In the study, two key challenges are primarily addressed: limitations of emotion lexicons, which may include ambiguous or misclassified words, and high-dimensional vector representations, which may increase computational complexity. To improve lexicon quality, which is an important data source in emotion enrichment studies, a filtering mechanism is introduced aiming to remove the words with inconsistent emotional associations, enhancing lexicon precision. Additionally, a sliding window-based dimensionality reduction method is applied to BERT embeddings to identify emotion-rich vector segments, reducing computational cost while preserving emotional information. Experiments are conducted in both English and Turkish to evaluate the impact of lexicon filtering and dimensionality reduction on emotion detection. Results show that filtering improves the accuracy of emotion-enriched representations, while sub-vector selection gives the possibility of finding more representative parts about emotional content. By focusing on emotion-relevant vector dimensions, the proposed method achieves superior performance compared to full-dimensional embeddings. This research contributes to multilingual emotion representation by refining lexicon-based enrichment strategies and optimizing embedding spaces for emotion detection. The findings highlight the importance of structured lexicon filtering and targeted dimensionality reduction in improving sentiment and emotion analysis models. © 2025 Elsevier B.V., All rights reserved.Conference Object Citation - Scopus: 3Multiword Expression Detection in Turkish Using Linguistic Features(Institute of Electrical and Electronics Engineers Inc., 2017) Metin, S.K.; Taze M.; Uymaz, H.A.; Okur E.Detection of multiword expressions is an important pre-task in several research topics such as natural language understanding, automatic text summarization, and machine translation in the area of natural language processing. In this study, detection of multiword expressions in Turkish texts is accepted as a classification problem. 6 types of linguistic features are defined solving this problem in Turkish texts. The classification tests are performed by 10 different classifiers utilizing the prepared data set. The performance of classifiers is measured for different sizes of random train-test sets by running the tests 10 times. The test results showed that linguistic features can be used in identification of multiword expressions. And it is observed that SMO and J48 algorithms reached the highest classification performances based on different evaluation metrics. © 2017 IEEE.Article Citation - WoS: 4Citation - Scopus: 8Emotion-Enriched Word Embeddings for Turkish(Pergamon-Elsevier Science Ltd, 2023) Uymaz, Hande Aka; Kumova Metin, SenemText, as one of the main communication methods, is frequently used as a data source for natural language processing (NLP) studies. Naturally, our thoughts, expressions, and actions are based on our feelings. Therefore, representing the language better to machines involves the problems of reflecting the actual meaning and also, the detecting emotion of the data source. While representing the textual data, word embeddings (e.g. Word2Vec and GloVe (Global Vectors for Word Representation)) which can extract semantic information are frequently used. However, these models may give unexpected results in sentiment and emotion detection studies because of the limitations of capturing emotive data. Because of occurring frequently in similar contexts, some words carrying opposite emotions may have similar vector representations. Nowadays, enriching the vectors by adding emotion or sentiment data is studied which aim to increase the success in emotion detection or classification tasks. The main purpose is to reorganize the vector space in a way that words having semantically and sentimentally similar in closer locations. In this study, three emotion enrichment models over two semantic embeddings (Word2Vec and GloVe) and a contextual embedding (BERT) (Bidirectional Encoder Representations from Transformers)) are applied to a Turkish dataset. Turkish is an agglutinative language. Thus, it is expected to produce different results in this problem, as it has a different structure from the languages that are frequently studied in this field. Besides, experiments on in-category/opposite-category cosine similarity based on eight emotion categories and classifi-cation with sequential minimal optimization, logistic regression and multi-layer perceptron are conducted. Ac-cording to experimental results emotionally enriched vector representations outperform the original models and give promising results.Article Enriching Transformer-Based Embeddings for Emotion Identification in an Agglutinative Language: Turkish(Ieee Computer Soc, 2023) Aka Uymaz, Hande; Kumova Metin, SenemText-based emotion detection is an important and expanding research area due to the increasing accessibility of written data via the Internet and social media. Vector space models, such as semantic and contextual methods, are frequently used in many domains in natural language processing. Currently, to improve performance in emotion/sentiment detection studies, a new research area has emerged, which involves adding extra emotion information (emotion enrichment) to these models. Furthermore, as emotion depends on multiple parameters, the success of enrichment may vary based on different languages. In this study, we applied two emotion-enrichment methods on emerging transformer-based models [bidirectional encoder representations from transformers (BERT), a robustly optimized BERT pretraining approach, a distilled version of BERT, and efficiently learning an encoder that classifies token replacements accurately] and a traditional semantic model (Word2Vec) (as a baseline) on the Turkish (a highly agglutinative language) dataset. The performance was analyzed with classification models and cosine-similarity metrics.Master Thesis Identification of Multiword Expressions in Turkish Based on Web Data(İzmir Ekonomi Üniversitesi, 2016) Uymaz, Hande Aka; Metin, Senem KumovaÇok sözcüklü ifade, doğal dillerde, sözcüklerin anlam bütünlüğü oluşturmak üzere tekrarlayan kombinasyonlarıdır. Metinlerden çok sözcüklü ifadelerin belirlenmesi bir çok doğal dil işleme uygulamaları ( Doğal dil üretme, hesaplamalı sözlükbilim, makine çevirileri vb.) için çok önemli bir konudur. çok sözcüklü ifadelerin belirlenmesi için gözlenme sıklığı bağımlı yöntemler ( Bileşik olasılık (joint probability), noktasal karşılıklı bilgi katsayısı (pointwise mutual information), karşılıklı bağlılık (mutual dependency) v.b) sıklıkla kullanılır. Bu yöntemlerin en büyük dezavantajı, çok sözcüklü ifadelerin belirlenmesinin performansının frekansın ölçüldüğü veri kaynağının büyüklüğüne bağlı olmasıdır. Bu tezin amacı, küçük veri setlerinin yarattığı problemlerin önüne geçmek için bilinen en büyük veri kaynağı olan web'i kullanarak gözlenme sıklığını elde etmektir. Bu tezde, 2 farklı aday veri seti kullanılarak, Türkçe dili için frekans tabanlı çok sözcüklü ifade belirleme metotlarının performansı araştırılmıştır. Veri setlerindeki adayların gözlenme sıklığı bilgisi popüler bir arama motoru olan Google kullanılarak elde edilmiştir. Aday çok sözcüklü ifadelerin arama motoruna sorgu olarak gönderildiğinde alınan sayfa sayısı (ing. page count) adayın gözlenme sıklığı olarak kabul edilmiştir. Kullanılan 20 yöntemin başarısı anma(recall), duyarlılık(precision) ve F-ölçütü (F-measure) ile değerlendirilmiştir. Web tabanlı frekans bilgisinin çok sözcüklü ifadelerin belirlenmesindeki performansı geleneksel derlem tabanlı frekans ile karşılaştırılmıştır ve çok sözcüklü ifadelerin belirlenmesinde web verilerinin kullanılması umut verici sonuçlar göstermiştir.Article Citation - Scopus: 1Exploring the Effectiveness of LLM-Generated Context on Emotion Lexicon Word Vectorization: A Comparative Study on Turkish and English(IEEE Computer Soc, 2025) Kumova Metin, Senem; Aka Uymaz, HandeThis study explores the impact of large language models (LLMs) on emotion lexicon word vectorization on Turkish and English. Emotion analysis involves extracting affective information from various data sources, with text being a primary medium. While traditional vectorization methods lack semantic meaning, contextual vectors, such as bidirectional encoder representations from transformers (BERT), aim to capture the context of words, leading to improved performance in natural language processing tasks. We investigate the efficacy of context sentences from human-annotated datasets and sentences generated by Gemini-Pro LLM in creating word vectors. Additionally, we introduce a manually annotated Turkish emotion and sentiment lexicon (TES-Lex). Performance evaluation is conducted for both Turkish and English using BERT vectors with two approaches: cosine similarity and machine learning. Our findings indicate that LLM-generated context sentences significantly enhance the quality of word vectors, especially in Turkish, underscoring the potential of LLMs in augmenting emotion lexicon resources in low-resourced languages.Conference Object Collaborative Emotion Annotation: Assessing the Intersection of Human and Ai Performance With Gpt Models(Science and Technology Publications, Lda, 2023) Uymaz, H.A.; Metin, S.K.In this study, we explore emotion detection in text, a complex yet vital aspect of human communication. Our focus is on the formation of an annotated dataset, a task that often presents difficulties due to factors such as reliability, time, and consistency. We propose an alternative approach by employing artificial intelligence (AI) models as potential annotators, or as augmentations to human annotators. Specifically, we utilize ChatGPT, an AI language model developed by OpenAI. We use its latest versions, GPT3.5 and GPT4, to label a Turkish dataset having 8290 terms according to Plutchik's emotion categories, alongside three human annotators. We conduct experiments to assess the AI's annotation capabilities both independently and in conjunction with human annotators. We measure inter-rater agreement using Cohen's Kappa, Fleiss Kappa, and percent agreement metrics across varying emotion categorizations- eight, four, and binary. Particularly, when we filtered out the terms where the AI models were indecisive, it was found that including AI models in the annotation process was successful in increasing inter-annotator agreement. Our findings suggest that, the integration of AI models in the emotion annotation process holds the potential to enhance efficiency, reduce the time of lexicon development and thereby advance the field of emotion/sentiment analysis. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)Conference Object Redefining Prerequisites Through Text Embeddings: Identifying Practical Course Dependencies(Science and Technology Publications, Lda, 2025) Tetik, Ş.K.; Toprak, E.; Kumova Metin, S.; Uymaz, H.A.This study proposes a framework to support undergraduate students in course selection by identifying implicit prerequisites and predicting performance in elective courses. Unlike traditional prerequisite rules that rely solely on curriculum design, our approach integrates students’ academic history and course-level semantic information. We define two core tasks: (T1) identifying practical prerequisites that significantly impact success in a target course, and (T2) predicting student success in elective courses based on academic profiles. For T1, we analyze prior course performance and learning outcomes using SHAP (SHapley Additive exPlanations) to determine the most influential courses. For T2, we build student representations using course descriptions and learning outcomes, then apply embedding models (Sentence-BERT, Doc2Vec, Universal Sentence Encoder) combined with classification algorithms to predict course success. Experiments demonstrate that embedding-based models, especially those using Sentence-BERT, can effectively predict course outcomes. The results suggest that incorporating semantic representations enhances curriculum design, course advisement, and prerequisite refinement. © © 2025 by SCITEPRESS – Science and Technology Publications, Lda.Doctoral Thesis From Words To Sentences: Advancing Turkish Emotion Analysis Through Emotion Enrichment(İzmir Ekonomi Üniversitesi, 2023) Aka Uymaz, Hande; Meti̇n, Senem KumovaDoğal dil işleme çalışmalarında dilin makineler tarafından anlaşılması, dilin doğru algılanması, veri kaynağındaki gerçek anlamın yakalanması ve duygusal nüansların ayırt edilmesi ihtiyacı nedenleriyle zorluklar içermektedir. Metinsel verileri temsil ederken mevcut kelime vektörleştirme modelleri anlamsal bilgilerin çıkarılmasında başarılıdır. Ancak bu modeller sıklıkla bir arada kullanılan kelimeleri vektör uzayında birbirine benzer şekilde temsil etmektedir. Bu nedenle, zıt duygulara sahip kelimeler, sık sık bir arada bulunmaları nedeniyle benzer vektör temsillerine sahip olabilir. Duygu tespitindeki bu tür eksikliklerin üstesinden gelmek için mevcut araştırmalar, duygusal bilgiler ekleyerek vektörleri zenginleştirmeye odaklanmaktadır. Vektör zenginleştirmede temel amaç, benzer semantik ve duygusal anlamlara sahip kelimelerin yakınlığını artırmak için vektör uzayını yeniden projekte etmektir. Bu çalışmada, iki semantik (Word2Vec ve GloVe) ve iki bağlamsal (BERT ve DistilBERT) vektörleştirme yöntemi kullanarak üç duygu zenginleştirme modeli Türkçe kelime ve cümlelere uygulanmıştır. Yapı itibariyle eklemeli bir dil olan Türkçenin bu bağlamda sıklıkla çalışılan diğer dillerden farklı sonuçlar üretmesi beklenmektedir. Sonuçlar, hem kelime hem de cümle düzeyinde zenginleştirmenin umut verici sonuçlarını göstermektedir. Zenginleştirilmiş cümle gösterimi literatürde ilk kez hem İngilizce hem de Türkçe dillerinde önerilmiştir. Ayrıca, herhangi bir dil ve vektör modeline uygulanabilen, duygu sözlüklerini filtreleme ve yüksek boyutlu vektörlerin boyutunu azaltarak duygusal bilgi içeren bölümleri belirleme amacını taşıyan bir optimizasyon yöntemi önerilmiştir. Deneysel sonuçlar, duygusal açıdan zenginleştirilmiş vektör temsillerinin orijinal modellerden daha iyi sonuçlar verdiğini göstermektedir.
