Search Results (12)

The rapid expansion of e-commerce has significantly influenced consumer purchasing behavior, making user reviews a critical source of product-related information. However, the large volume of low-quality and superficial reviews limits the ability to obtain reliable insights. This study aims to classify Turkish e-commerce reviews as either useful or useless, thereby highlighting high-quality content to support more informed consumer decisions. A dataset of 15,170 Turkish product reviews collected from major e-commerce platforms was analyzed using traditional machine learning approaches, including Support Vector Machines and Logistic Regression, and transformer-based models such as BERT and RoBERTa. In addition, a novel Multi-Transformer Fusion Framework (MTFF) was proposed by integrating BERT and RoBERTa representations through concatenation, weighted-sum, and attention-based fusion strategies. Experimental results demonstrated that the concatenation-based fusion model achieved the highest performance with an F1-score of 91.75%, outperforming all individual models. Among standalone models, Turkish BERT achieved the best performance (F1: 89.37%), while the BERT + Logistic Regression hybrid approach yielded an F1-score of 88.47%. The findings indicate that multi-transformer architectures substantially enhance classification performance, particularly for agglutinative languages such as Turkish. To improve the interpretability of the proposed framework, SHAP (SHapley Additive exPlanations) was employed to analyze feature contributions and provide transparent explanations for model predictions, revealing that the model primarily relies on experience-oriented and semantically meaningful linguistic cues. The proposed approach can support e-commerce platforms by automatically prioritizing high-quality and informative reviews, thereby improving user experience and decision-making processes. Full article

In the current information age, with the exponential growth of data volume and language-based applications, the accurate resolution of intra-contextual relationships in texts has become indispensable for both academic research and industrial Natural Language Processing (NLP) systems. This study focuses on the detection of pronominal anaphora in Turkish sentences. For the detection of pronominal anaphora, a specific dataset comprising 2000 sentences and 72,239 tokens was created, and this dataset was labeled using a BIO tagging method developed with a custom approach for this study. In this work, fine-tuning was performed on Transformer-based language models pre-trained on Turkish data, such as BERT and RoBERTa. Additionally, Large Language Models (LLMs) trained on Turkish data, including Turkcell-LLM-7b-v1 and ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1, as well as multilingual models like Microsoft’s Phi-3 Mini-4K-Instruct and OpenAI’s GPT-4o-mini, were also fine-tuned with the created dataset to detect pronominal anaphora in sentences. Following the training of the language models, the resulting performance was evaluated using pronoun accuracy, antecedent accuracy, exact match, and F1-score metrics. According to the results obtained in the pronominal anaphora detection phase of the study, a novel hybrid ensemble approach combining multiple Transformer models with linguistic rules achieved the highest performance. This hybrid system attained scores of 0.987 for pronoun accuracy, 0.977 for antecedent accuracy, 0.505 for exact match, and 0.960 for F1-score, surpassing all individual models, including GPT-4o-mini. These findings reveal the superiority of ensemble methods combined with Turkish-specific linguistic rules over standalone models in Turkish anaphora resolution. This study is considered novel, as it is the first work to apply hybrid ensemble methods with linguistic rule integration to this domain for the Turkish language. Full article

Across digital platforms, large-scale assessment of customer sentiment has become integral to brand management, service recovery, and data-driven marketing in e-commerce. Still, most studies center on single-language settings, with bilingual and culturally diverse environments receiving comparatively limited attention. In this study, a bilingual sentiment analysis of consumer feedback on X (formerly Twitter) was conducted for three global quick-service restaurant (QSR) brands—McDonald’s, Burger King, and KFC—using 145,550 English tweets and 15,537 Turkish tweets. After pre-processing and leakage-safe augmentation for low-resource Turkish data, both traditional machine learning models (Naïve Bayes, Support Vector Machines, Logistic Regression, Random Forest) and a transformer-based deep learning model, BERT (Bidirectional Encoder Representations from Transformers), were evaluated. BERT achieved the highest performance (macro-F1 ≈ 0.88 in Turkish; ≈0.39 in temporally split English), while Random Forest emerged as the strongest ML baseline. An apparent discrepancy was observed between pseudo-label agreement (Accuracy > 0.95) and human-label accuracy (EN: 0.75; TR: 0.49), indicating the limitations of lexicon-derived labels and the necessity of human validation. Beyond methodological benchmarking, linguistic contrasts were identified: English tweets were more polarized (positive/negative), whereas Turkish tweets were overwhelmingly neutral. These differences reflect cultural patterns of online expression and suggest direct managerial implications. The findings indicate that bilingual sentiment analysis yields brand-level insights that can inform strategic and operational decisions. Full article

Identifying age-appropriate books for children is a complex task that requires balancing linguistic, cognitive, and thematic factors. This study introduces an artificial intelligence–supported framework to estimate the Suitable Age Value (SAV) of Turkish children’s books targeting the 2–18-year age range. We employ repeated, stratified $5\times 5$ cross-validation and report out-of-fold (OOF) metrics with 95% confidence intervals for a dataset of 300 Turkish children’s books. As classical baselines, linear/ElasticNet, SVR, Random Forest (RF), and XGBoost are trained on the engineered features; we also evaluate a rule-based Ateşman readability baseline. For text, we use a frozen dbmdz/bert-base-turkish-uncased encoder inside two hybrid variants, Concat and Attention-gated, with fold-internal PCA and metadata selection; augmentation is applied only to the training folds. Finally, we probe a few-shot LLM pipeline (GPT-4o-mini) and a convex blend of RF and LLM predictions. A few-shot LLM markedly outperforms the zero-shot model, and zero-shot performance is unreliable. Among hybrids, Concat performs better than Attention-gated, yet both trail our best classical baseline. A convex RF + LLM blend, learned via bootstrap out-of-bag sampling, achieves a lower RMSE/MAE than either component and a slightly higher QWK. The Ateşman baseline performance is substantially weaker. Overall, the findings were as follows: feature-based RF remains a strong baseline, few-shot LLMs add semantic cues, blending consistently helps, and simple hybrid concatenation beats a lightweight attention gate under our small-N regime. Full article

Accurate gender identification from written text is critical for author profiling, recommendation systems, and demographic analytics in digital ecosystems. This study introduces a scalable framework for gender classification in Turkish, combining contextualized BERTurk and subword-aware FastText embeddings with three meta-heuristic feature selection algorithms: Genetic Algorithm (GA), Jaya and Artificial Rabbit Optimization (ARO). Evaluated on the IAG-TNKU corpus of 43,292 balanced Turkish news articles, the best-performing model—BERTurk+GA+LSTM—achieves 89.7% accuracy, while ARO reduces feature dimensionality by 90% with minimal performance loss. Beyond in-domain results, exploratory zero-shot and few-shot adaptation experiments on Turkish e-commerce product reviews demonstrate the framework’s transferability: while zero-shot performance dropped to 59.8%, few-shot adaptation with only 200–400 labeled samples raised accuracy to 69.6–72.3%. These findings highlight both the limitations of training exclusively on news articles and the practical feasibility of adapting the framework to consumer-generated content with minimal supervision. In addition to technical outcomes, we critically examine ethical considerations in gender inference, including fairness, representation, and the binary nature of current datasets. This work contributes a reproducible and linguistically informed baseline for gender profiling in morphologically rich, low-resource languages, with demonstrated potential for adaptation across domains such as social media and e-commerce personalization. Full article

Sentiment analysis in the Turkish language has gained increasing attention due to the growing availability of Turkish textual data across various domains. However, existing datasets often suffer from limitations such as insufficient size, lack of diversity, and annotation inconsistencies, which hinder the development of robust and accurate sentiment analysis models. In this study, we present a novel enhanced dataset specifically designed to address these challenges, providing a comprehensive and high-quality resource for Turkish sentiment analysis. We perform a comparative evaluation of previously proposed models using our dataset to assess their performance and limitations. Experimental findings demonstrate the effectiveness of the presented dataset and trained models, offering valuable insights for advancing sentiment analysis research in the Turkish language. These results underscore the critical role of the enhanced dataset in bridging the gap between existing datasets and the importance of training the modern sentiment analysis models on scalable, balanced, and curated datasets. This can offer valuable insights for advancing sentiment analysis research in the Turkish language. Furthermore, the experimental results represent an important step in overcoming the challenges associated with Turkish sentiment analysis and improving the performance of existing models. Full article

This article provides a comprehensive survey of contemporary language modeling approaches within the realm of natural language processing (NLP) tasks. This paper conducts an analytical exploration of diverse methodologies employed in the creation of language models. This exploration encompasses the architecture, training processes, and optimization strategies inherent in these models. The detailed discussion covers various models ranging from traditional n-gram and hidden Markov models to state-of-the-art neural network approaches such as BERT, GPT, LLAMA, and Bard. This article delves into different modifications and enhancements applied to both standard and neural network architectures for constructing language models. Special attention is given to addressing challenges specific to agglutinative languages within the context of developing language models for various NLP tasks, particularly for Arabic and Turkish. The research highlights that contemporary transformer-based methods demonstrate results comparable to those achieved by traditional methods employing Hidden Markov Models. These transformer-based approaches boast simpler configurations and exhibit faster performance during both training and analysis. An integral component of the article is the examination of popular and actively evolving libraries and tools essential for constructing language models. Notable tools such as NLTK, TensorFlow, PyTorch, and Gensim are reviewed, with a comparative analysis considering their simplicity and accessibility for implementing diverse language models. The aim is to provide readers with insights into the landscape of contemporary language modeling methodologies and the tools available for their implementation. Full article

Requirements Engineering (RE) is an important step in the whole software development lifecycle. The problem in RE is to determine the class of the software requirements as functional (FR) and non-functional (NFR). Proper and early identification of these requirements is vital for the entire development cycle. On the other hand, manual identification of these classes is a timewaster, and it needs to be automated. Methodically, machine learning (ML) approaches are applied to address this problem. In this study, twenty ML algorithms, such as Naïve Bayes, Rotation Forests, Convolutional Neural Networks, and transformers such as BERT, were used to predict FR and NFR. Any ML algorithm requires a dataset for training. For this goal, we generated a unique Turkish dataset having collected the requirements from real-world software projects with 4600 samples. The generated Turkish dataset was used to assess the performance of the three groups of ML algorithms in terms of F-score and related statistical metrics. In particular, out of 20 ML algorithms, BERTurk was found to be the most successful algorithm for discriminating FR and NFR in terms of a 95% F-score metric. From the FR and NFR identification problem point of view, transformer algorithms show significantly better performances. Full article

Spam communications from spam ads and social media platforms such as Facebook, Twitter, and Instagram are increasing, making spam detection more popular. Many languages are used for spam review identification, including Chinese, Urdu, Roman Urdu, English, Turkish, etc.; however, there are fewer high-quality datasets available for Urdu. This is mainly because Urdu is less extensively used on social media networks such as Twitter, making it harder to collect huge volumes of relevant data. This paper investigates policy-based Urdu tweet spam detection. This study aims to collect over 1,100,000 real-time tweets from multiple users. The dataset is carefully filtered to comply with Twitter’s 100-tweet-per-hour limit. For data collection, the snscrape library is utilized, which is equipped with an API for accessing various attributes such as username, URL, and tweet content. Then, a machine learning pipeline consisting of TF-IDF, Count Vectorizer, and the following machine learning classifiers: multinomial naïve Bayes, support vector classifier RBF, logical regression, and BERT, are developed. Based on Twitter policy standards, feature extraction is performed, and the dataset is separated into training and testing sets for spam analysis. Experimental results show that the logistic regression classifier has achieved the highest accuracy, with an F1-score of 0.70 and an accuracy of 99.55%. The findings of the study show the effectiveness of policy-based spam detection in Urdu tweets using machine learning and BERT layer models and contribute to the development of a robust Urdu language social media spam detection method. Full article

English is accepted as an academic language in the world. This necessitates the use of English in their academic studies for speakers of other languages. Even when these researchers are competent in the use of the English language, some mistakes may occur while writing an academic article. To solve this problem, academicians tend to use automatic translation programs or get assistance from people with an advanced level of English. This study offers an expert system to enable assistance to the researchers throughout their academic article writing process. In this study, Turkish which is considered among low-resource languages is used as the source language. The proposed model combines the transformer encoder-decoder architecture model with the pre-trained Sci-BERT language model via the shallow fusion method. The model uses a Fully Attentional Network Layer instead of a Feed-Forward Network Layer in the known shallow fusion method. In this way, a higher success rate could be achieved by increasing the attention at the word level. Different metrics were used to evaluate the created model. The model created as a result of the experiments reached 45.1 BLEU and 73.2 METEOR scores. In addition, the proposed model achieved 20.12 and 20.56 scores, respectively, with the zero-shot translation method in the World Machine Translation (2017–2018) test datasets. The proposed method could inspire other low-resource languages to include the language model in the translation system. In this study, a corpus composed entirely of academic sentences is also introduced to be used in the translation system. The corpus consists of 1.2 million parallel sentences. The proposed model and corpus are made available to researchers on our GitHub page. Full article

This paper reviews the most recent literature on experiments with different Machine Learning, Deep Learning and Natural Language Processing techniques applied to predict judicial and administrative decisions. Among the most outstanding findings, we have that the most used data mining techniques are Support Vector Machine (SVM), K Nearest Neighbours (K-NN) and Random Forest (RF), and in terms of the most used deep learning techniques, we found Long-Term Memory (LSTM) and transformers such as BERT. An important finding in the papers reviewed was that the use of machine learning techniques has prevailed over those of deep learning. Regarding the place of origin of the research carried out, we found that 64% of the works belong to studies carried out in English-speaking countries, 8% in Portuguese and 28% in other languages (such as German, Chinese, Turkish, Spanish, etc.). Very few works of this type have been carried out in Spanish-speaking countries. The classification criteria of the works have been based, on the one hand, on the identification of the classifiers used to predict situations (or events with legal interference) or judicial decisions and, on the other hand, on the application of classifiers to the phenomena regulated by the different branches of law: criminal, constitutional, human rights, administrative, intellectual property, family law, tax law and others. The corpus size analyzed in the reviewed works reached 100,000 documents in 2020. Finally, another important finding lies in the accuracy of these predictive techniques, reaching predictions of over 60% in different branches of law. Full article

Unlike the traditional model, the end-to-end (E2E) ASR model does not require speech information such as a pronunciation dictionary, and its system is built through a single neural network and obtains performance comparable to that of traditional methods. However, the model requires massive amounts of training data. Recently, hybrid CTC/attention ASR systems have become more popular and have achieved good performance even under low-resource conditions, but they are rarely used in Central Asian languages such as Turkish and Uzbek. We extend the dataset by adding noise to the original audio and using speed perturbation. To develop the performance of an E2E agglutinative language speech recognition system, we propose a new feature extractor, MSPC, which uses different sizes of convolution kernels to extract and fuse features of different scales. The experimental results show that this structure is superior to VGGnet. In addition to this, the attention module is improved. By using the CTC objective function in training and the BERT model to initialize the language model in the decoding stage, the proposed method accelerates the convergence of the model and improves the accuracy of speech recognition. Compared with the baseline model, the character error rate (CER) and word error rate (WER) on the LibriSpeech test-other dataset increases by 2.42% and 2.96%, respectively. We apply the model structure to the Common Voice—Turkish (35 h) and Uzbek (78 h) datasets, and the WER is reduced by 7.07% and 7.08%, respectively. The results show that our method is close to the advanced E2E systems. Full article