Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
5 results
Search Results
Article Citation - WoS: 1Citation - Scopus: 1Author Reputation Measurement on Question and Answer Sites by the Classification of Author-Generated Content(World Scientific Publishing, 2021) Sezerer, Erhan; Tenekeci, Samet; Acar, Ali; Baloğlu, Bora; Tekir, SelmaIn the field of software engineering, practitioners' share in the constructed knowledge cannot be underestimated and is mostly in the form of grey literature (GL). GL is a valuable resource though it is subjective and lacks an objective quality assurance methodology. In this paper, a quality assessment scheme is proposed for question and answer (Q&A) sites. In particular, we target stack overflow (SO) and stack exchange (SE) sites. We model the problem of author reputation measurement as a classification task on the author-provided answers. The authors' mean, median, and total answer scores are used as inputs for class labeling. State-of-the-art language models (BERT and DistilBERT) with a softmax layer on top are utilized as classifiers and compared to SVM and random baselines. Our best model achieves 63.8% accuracy in binary classification in SO design patterns tag and 71.6% accuracy in SE software engineering category. Superior performance in SE software engineering can be explained by its larger dataset size. In addition to quantitative evaluation, we provide qualitative evidence, which supports that the system's predicted reputation labels match the quality of provided answers.Article Citation - WoS: 2Citation - Scopus: 2Incorporating Concreteness in Multi-Modal Language Models With Curriculum Learning(MDPI, 2021) Sezerer, Erhan; Tekir, SelmaOver the last few years, there has been an increase in the studies that consider experiential (visual) information by building multi-modal language models and representations. It is shown by several studies that language acquisition in humans starts with learning concrete concepts through images and then continues with learning abstract ideas through the text. In this work, the curriculum learning method is used to teach the model concrete/abstract concepts through images and their corresponding captions to accomplish multi-modal language modeling/representation. We use the BERT and Resnet-152 models on each modality and combine them using attentive pooling to perform pre-training on the newly constructed dataset, which is collected from the Wikimedia Commons based on concrete/abstract words. To show the performance of the proposed model, downstream tasks and ablation studies are performed. The contribution of this work is two-fold: A new dataset is constructed from Wikimedia Commons based on concrete/abstract words, and a new multi-modal pre-training approach based on curriculum learning is proposed. The results show that the proposed multi-modal pre-training approach contributes to the success of the model.Conference Object Citation - WoS: 2Citation - Scopus: 4Çok-etiketli Film Türü Sınıflandırması için Türkçe Konu Modellemesi Veri Kümesi(Institute of Electrical and Electronics Engineers, 2020) Jabrayilzade, Elgün; Poyraz Arslan, Algın; Para, Hasan; Polatbilek, Ozan; Sezerer, Erhan; Tekir, SelmaStatistical topic modeling aims to assign topics to documents in an unsupervised way. Latent Dirichlet Allocation (LDA) is the standard model for topic modeling. It shows good performance on document collections, documents being relatively long texts but it has poor performance on short texts. Topic modeling on short texts is on the rise due to the potential of social media. Thus, approaches that are able to nd topics on short texts as well as long texts are sought. However, there is a lack of datasets that include both long and short texts which have the same ground-truth categories. In this work, we release a Turkish movie dataset which contain both short lm descriptions and long subscripts where lm genre can be considered as topic. Furthermore, we provide multi-label movie genre classication results using a Feed Forward Neural Network (FFNN) taking LDA document-topic or Doc2Vec dense representations. © 2020 IEEE.Conference Object Citation - Scopus: 1Türkçe Tweetler Üzerinden Yapay Sinir Ağları ile Cinsiyet Tahminlemesi(Institute of Electrical and Electronics Engineers Inc., 2019) Sezerer, Erhan; Polatbilek, Ozan; Tekir, SelmaYazar ayrımlaması, yazarı bilinmeyen bir metin üzerinden yazarına dair cinsiyet, yaş ve dil gibi bazı anahtar özniteliklerin belirlenmesidir. Özellikle güvenlik ve pazarlama alanında önem arz etmektedir. Bu çalışmada, kullanıcıların tweetleri kullanılarak cinsiyetleri tahminlenmektedir. Yinelemeli Sinir Ağı (YSA) ve ilgi mekanizmasının birleşiminden oluşan bir model önerilmiştir. Bildiğimiz kadarıyla bu çalışma Twitter veri kümesi ile Türkçe’de ilk defa yapılmıştır. Önerilen model Türkçe, İngilizce, İspanyolca ve Arapça dillerinde sınanmış ve sırasıyla 80.63, 81.73, 78.22, 78.5 doğruluk değerlerine ulaşılmıştır. Elde edilen doğruluk değerleri Türkçe’de en gelişkin, diğer dillerde ise rekabetçi bir başarım ortaya koymaktadır.Conference Object Citation - WoS: 1Citation - Scopus: 1A Relativistic Opinion Mining Approach To Detect Factual or Opinionated News Sources(Springer Verlag, 2017) Sezerer, Erhan; Tekir, SelmaThe credibility of news cannot be isolated from that of its source. Further, it is mainly associated with a news source’s trustworthiness and expertise. In an effort to measure the trustworthiness of a news source, the factor of “is factual or opinionated” must be considered among others. In this work, we propose an unsupervised probabilistic lexicon-based opinion mining approach to describe a news source as “being factual or opinionated”. We get words’ positive, negative, and objective scores from a sentiment lexicon and normalize these scores through the use of their cumulative distribution. The idea behind the use of such a statistical approach is inspired from the relativism that each word is evaluated with its difference from the average word. In order to test the effectiveness of the approach, three different news sources are chosen. They are editorials, New York Times articles, and Reuters articles, which differ in their characteristic of being opinionated. Thus, the experimental validation is done by the analysis of variance on these different groups of news. The results prove that our technique can distinguish the news articles from these groups with respect to “being factual or opinionated” in a statistically significant way.