This study aims to investigate the performance of test equating methods extended to mixed-format tests within the framework of Item Response Theory (IRT). To this end, a simulation study was conducted to compare equating errors of the mean/mean, mean/sigma, robust mean/sigma, Haebara, and Stocking-Lord methods under different conditions. Using 40-item tests, the effects of anchor length (10%, 20%, and 30%) and ability distribution (normal, negatively skewed, and positively skewed) were examined on a sample of 1000 participants. We used the common-item nonequivalent group design. The tests were developed using the three parameter logistic model for dichotomous simulated data and the generalized partial credit model for polytomous simulated data. The results of the study revealed that the robust mean/sigma method generally had the highest equating errors. When all conditions were evaluated, the least equating error occurred with the "Stocking-Lord" method in the case of positively skewed groups and a long anchor test (30%). Moreover, the results indicated that the groups with similar ability distributions (normal-normal, negatively skewednegatively skewed, and positively skewed-positively skewed) produced less equation errors than the groups with different ability distributions (negatively skewed-normal, positively skewed-normal, and positively skewed-negatively skewed).

A r ş . G ö r . Me r v e Ş A H İ N -A r ş . G ö r . İ b r a h i m U Y S A LÖ ğ r e t me n A d a y l a r ı n ı n Ö l ç me v e D e ğ e r l e n d i r me K o n u s u n d a k i Ö z -Y e t

Abstract-Semantic Role Labeling (SRL) aims to identify the constituents of a sentence, together with their roles with respect to the sentence predicates. In this paper, we introduce and assess the idea of using SRL on generic Multi-Document Summarization (MDS). We score sentences according to their inclusion of frequent semantic phrases and form the summary using the top-scored sentences. We compare this method with a term-based sentence scoring approach to investigate the effects of using semantic units instead of single words for sentence scoring. We also integrate our scoring metric as an auxiliary feature to a cutting edge summarizer with the intention of examining its effects on the performance. The experiments using datasets from the Document Understanding Conference (DUC) 2004 show that the SRL-based summarization outperforms the term-based approach as well as most of the DUC participants.

 İbrahim UYSAL  Güler DUMAN  Elif YAZICI  Merve ŞAHİN  ÖzSon yıllarda bilgi ve iletişim teknolojilerinde yaşanan gelişmeler, zorbalığının yeni bir biçimi olan siber zorbalık kavramını ortaya çıkarmıştır. Siber zorbalık insanların hayatlarını olumsuz yönde etkileyen toplumsal bir sorun haline gelmiştir. Siber zorbalığın olumsuz yönlerini azaltmada ve siber zorbalık ile başa çıkmada anahtar unsur ise siber zorbalık duyarlılığına sahip olmaktır. Bu araştırmanın amacı, öğretmen adaylarının siber zorbalık duyarlılıklarını cinsiyet ve bölüm değişkenleri açısından incelemektir. Tarama modelinin kullanıldığı bu araştırma, Batı Karadeniz Bölgesindeki bir üniversitenin Eğitim Fakültesinde öğrenim görmekte olan 296 öğretmen adayı üzerinde gerçekleştirilmiştir. Araştırmada veri toplama aracı olarak Tanrıkulu, Kınay ve Arıcak (2013) tarafından geliştirilen "Siber Zorbalığa ilişkin Duyarlılık Ölçeği" kullanılmıştır ve nicel veriler 2012-2013 öğretim yılı yaz döneminde toplanmıştır. Verilerin analizinde "Mann Whitney U Test" ve "Doğrulayıcı Faktör Analizi" kullanılmıştır. Araştırma sonucunda öğretmen adaylarının siber zorbalık duyarlılıklarının yüksek olduğu fakat cinsiyet ve bölüme göre anlamlı bir şekilde farklılaşmadığı sonucuna ulaşılmıştır. Çalışmanın siber zorbalığa ilişkin farkındalığı da ortaya çıkardığı dikkate alınarak bu farkındalığın çeşitli değişkenlerle birlikte incelenmesi ve sonuçların karşılaştırılması önerilebilir. Ayrıca nitel ve nicel çalışmalar aynı araştırmada kullanılarak siber zorbalık duyarlılığı konusunda derinlemesine bilgi edinilebilir. Cyberbullying has become a social concern affecting people's lives negatively similar to bullying. The sensibility towards cyberbullying is the key factor to minimize the negative effects of cyberbullying and get ready for managing cyberbullying. This study aimed to examine preservice sensibility towards cyberbullying in terms of demographic variables such as gender and department. A survey method was adopted in the study and data were collected from 296 pre-service teachers studying at education faculty of a university in the western Black Sea region. "Cyberbullying Sensibility Scale" developed by Tanrıkulu, Kınay and Arıcak (2013) was used as the data collection instrument to collect the quantitative data during the spring term of 2012-2013 academic year. In the data analysis process "Mann Whitney U Test" and "Confirmatory Factor Analysis" was computed. The results indicated that although the pre-service teachers had a high level of sensibility towards cyberbullying, their sensibility levels did not differ depending on their genders and departments. Reflecting on these results, the study revealed pre-service teachers' sensibility towards cyberbullying, so future studies could be conducted across different settings with different variables in order to present a more complete picture of cyberbullying. Also, mixed methods studies could be carried out to provide in-depth information about sensibility towards cyberbullying.

The increasing volume of streaming data on microblogs has re-introduced the necessity of effective filtering mechanisms for such media. Microblog users are overwhelmed with mostly uninteresting pieces of text in order to access information of value. In this paper, we propose a personalized tweet ranking method, leveraging the use of retweet behavior, to bring more important tweets forward. In addition, we also investigate how to determine the audience of tweets more effectively, by ranking the users based on their likelihood of retweeting the tweets. Finally, conducting a pilot user study, we analyze how retweet likelihood correlates with the interestingness of the tweets.