Skip to main content

Research Repository

Advanced Search

Outputs (110)

Learners Thrive When Using Multifaceted Open Social Learner Models (2015)
Journal Article
Shi, L., & Cristea, A. I. (2015). Learners Thrive When Using Multifaceted Open Social Learner Models. IEEE MultiMedia, 23(1), 36-47. https://doi.org/10.1109/mmul.2015.93

This article explores open social learner modeling (OSLM)-a social extension of open learner modeling (OLM). A specific implementation of this approach is presented by which learners' self-direction and self-determination in a social e-learning conte... Read More about Learners Thrive When Using Multifaceted Open Social Learner Models.

WarwickDCS : from phrase-based to target-specific sentiment recognition (2015)
Presentation / Conference Contribution
Townsend, R., Tsakalidis, A., Zhou, Y., Wang, B., Liakata, M., Zubiaga, A., Cristea, A., & Procter, R. (2015, June). WarwickDCS : from phrase-based to target-specific sentiment recognition. Presented at 9th International Workshop on Semantic Evaluation (SemEval 2015), Denver

We present and evaluate several hybrid systems for sentiment identification for Twitter, both at the phrase and document (tweet) level. Our approach has been to use a novel combination of lexica, traditional NLP and deep learning features. We also an... Read More about WarwickDCS : from phrase-based to target-specific sentiment recognition.

Predicting elections for multiple countries using Twitter and polls (2015)
Journal Article
Tsakalidis, A., Papadopoulos, S., Cristea, A., & Kompatsiaris, Y. (2015). Predicting elections for multiple countries using Twitter and polls. IEEE Intelligent Systems, 30(2), 10-17. https://doi.org/10.1109/mis.2015.17

The authors' work focuses on predicting the 2014 European Union elections in three different countries using Twitter and polls. Past works in this domain relying strictly on Twitter data have been proven ineffective. Others, using polls as their grou... Read More about Predicting elections for multiple countries using Twitter and polls.

The Critical Role of Profiles in Social E-Learning Design (2014)
Presentation / Conference Contribution
Shi, L., Cristea, A. I., & Hadzidedic, S. (2014, October). The Critical Role of Profiles in Social E-Learning Design. Presented at 15th Annual Conference on Information Technology Education (SIGITE), Atlanta, Georgia, US

Evidence points to the fact that the integration of Social Networking Sites (SNS) features, into e-learning environments has been highly accepted by students, because of its benefits of improving the learning experience. Yet, not enough attention has... Read More about The Critical Role of Profiles in Social E-Learning Design.

Multifaceted open social learner modelling (2014)
Book Chapter
Shi, L., Cristea, A., & Hadzidedic, S. (2014). Multifaceted open social learner modelling. In P. Elvira, R. W. Lau, K. Pata, H. Leung, & L. Mart (Eds.), Advances in Web-Based Learning – ICWL 2014, 13th International Conference, Tallinn, Estonia, August 14-17, 2014, Proceedings (32-42). Springer Verlag. https://doi.org/10.1007/978-3-319-09635-3_4

Open social learner modelling (OSLM) approaches are promoted in order to assist learners in self-directed and self-determined learning in a social context. Still, most approaches only focus on visualising learners’ performance, or providing complex t... Read More about Multifaceted open social learner modelling.

The ethical and social implications of personalization technologies for e-learning (2014)
Journal Article
Ashman, H., Brailsford, T., Cristea, A., Sheng, Q. Z., Stewart, C., Toms, E. G., & Wade, V. (2014). The ethical and social implications of personalization technologies for e-learning. Information and Management, 51(6), 819-832. https://doi.org/10.1016/j.im.2014.04.003

Personalization in information systems can be considered beneficial but also ethically and socially harmful. Like many other technologies, the uptake of personalization has been rapid, with inadequate consideration given to its effects. Personalizati... Read More about The ethical and social implications of personalization technologies for e-learning.

Entropy-based automated wrapper generation for weblog data extraction (2013)
Journal Article
Gkotsis, G., Stepanyan, K., Cristea, A., & Joy, M. (2013). Entropy-based automated wrapper generation for weblog data extraction. World Wide Web, 17(4), 827-846. https://doi.org/10.1007/s11280-013-0269-6

This paper proposes a fully automated information extraction methodology for weblogs. The methodology integrates a set of relevant approaches based on the use of web feeds and processing of HTML for the extraction of weblog properties. The approach i... Read More about Entropy-based automated wrapper generation for weblog data extraction.

Towards understanding learning behavior patterns in social adaptive personalized e-learning systems (2013)
Presentation / Conference Contribution
Shi, L., Cristea, A., Awan, M., Stewart, C., & Hendrix, M. (2013, May). Towards understanding learning behavior patterns in social adaptive personalized e-learning systems. Presented at 19th Americas Conference on Information Systems, Chicago

Implicit user modeling has always long since played an important role in supporting personalized web-based e-learning environments and is increasingly important in other learning environments such as serious games. Its main concern is to unobtrusivel... Read More about Towards understanding learning behavior patterns in social adaptive personalized e-learning systems.

Zero-cost labelling with web feeds for weblog data extraction (2013)
Presentation / Conference Contribution
Gkotsis, G., Stepanyan, K., Cristea, A., & Joy, M. (2013, May). Zero-cost labelling with web feeds for weblog data extraction. Presented at 23rd International World Wide Web Conference (WWW 2013)