Research Interests: Social Computing, Recommender Systems, Computational Social Science, Web Science, Data Science
About: Ass.-Prof. Dr. Elisabeth Lex is assistant professor at Graz University of Technology (TUG) and head of the Social Computing Lab at TUG and Know-Center. Her research interests include Social Computing, Recommender Systems, Computational Social Science, Web Science and Open Science. Elisabeth was work package leader in the FP7 IP Learning Layers, and scientific coordinator of the Marie Curie IRSES Web Information Quality Evaluation Initiative (WIQ-EI) project. She was task leader in the H2020 Analytics for Everyday Learning (AFEL) project where she researched on novel recommender systems and on opinion dynamics in online collaboration networks. Elisabeth was of the Expert Group on Altmetrics, which advised the European Commission, DG Research and Innovation. The expert group developed policies for the commission on how to use altmetrics to assess the impact of scientific artefacts. Elisabeth has published more than 60 scientific publications in venues such as the ACM World Wide Web Conference (WWW), ACM Conference on Hypertext and Social Media (HT), ACM Conference on Recommender Systems, as well as in journals such as Social Network Analysis and Mining (SNAM), Computational Social Networks (CSN), Scientometrics, Frontiers in Resarch Metrics & Analytics and the International Journal of Human–Computer Interaction on Recommender Systems, Social Network Analysis, Altmetrics, Data Mining, and Machine Learning and she has given several invited talks in the mentioned fields. Elisabeth regularly acts as Senior PC member, PC member and co-organizes and co-chairs a number of workshops and conferences at venues such as ACM IUI, ACM Web Science or OpenSym. Among other courses at Graz University of Technology, Elisabeth teaches Web Science, as well as Computational Social Systems I + II.
Selected Publications (see full list under Publications):
- Lacic, E., Reiter-Haas, M., Slawicek, V., Lex, E. (2019) Should we Embed? A Study on the Online Performance of Utilizing Embeddings for Real-Time Job Recommendations. Accepted for publication at 13th ACM Conference on Recommender Systems (RecSys)
- Hasani-Mavriqi, Kowald, D., Helic, D., Lex, E. (2018) Consensus Dynamics in Online Collaboration Systems. In Computational Social Networks, Springer.
- Seitlinger, P. Ley, T., Kowald, D., Theiler, D., Hasani-Mavriqi, I., Dennerlein, S., Lex, E., Albert, D. (2017) Balancing the fluency-consistency tradeoff in collaborative information search with a recommender approach. International Journal of Human–Computer Interaction.
- Kowald, D., Pujari, S., Lex, E. (2017) Temporal Effects on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach. In Proceedings of the 26th International World Wide Web Conference (WWW). ACM.
- Kopeinik, S., Kowald, D., Hasani-Mavriqi, I., Lex, E. (2017) Improving Collaborative Filtering Using a Cognitive Model of Human Category Learning. In The Journal of Web Science, Vol. 2, No. 1
- Kowald, D., Kopeinik, S., & Lex, E. (2017). The TagRec Framework as a Toolkit for the Development of Tag-Based Recommender Systems. In Proceedings of the Adjunct Publication of the 25th ACM International Conference on User Modeling, Adapation and Personalization (UMAP’2017). ACM.
- Hasani-Mavriqi, I., Geigl, F., Pujari, S.C., Lex, E., Helic, D. (2016) The influence of social status and network structure on consensus building in collaboration networks. In Social Network Analysis and Mining 6 (1), 80 (SNAM). doi:10.1007/s13278-016-0389-y
- Kowald, D., Lex, E. (2016) The Influence of Frequency, Recency and Semantic Context on the Reuse of Tags in Social Tagging Systems. In Proceedings of the 27th ACM Conference on Hypertext and Hypermedia (HT)
- Peters, I., Kraker, P., Lex, E., Gumpenberger, C., and Gorraiz, J. (2016) Research data explored: an extended analysis of citations and altmetrics. Scientometrics. http://dx.doi.org/10.1007/s11192-016-1887-4
- Kowald, D. and Lex, E. (2015) Evaluating Tag Recommender Algorithms in Real-World Folksonomies: A Comparative Study. In Proceedings of the 9th ACM Recommender Systems Conference (RecSys)
- Seitlinger, P., Kowald, D., Kopeinik, S., Hasani-Mavriqi, I., Ley, T., and Lex, E. (2015) Attention Please! A Hybrid Resource Recommender Mimicking Attention-Interpretation Dynamics. In 24rd International World Wide Web Conference (WWW), Web-Science Track, Companion Volume, New York: ACM.
Selected Community Activities:
- Senior PC at ACM IUI 2019 + 2018
- Senior PC at ACM Web Science 2019
- Senior PC at Social Informatics 2019
- Associate Chair at OpenSym 2017
- Best Paper Judging Committee ACM Web Science 2015
Want to collaborate? Contact me! elisabeth dot lex at tugraz dot at
If you are interested in collaboration, and/or in doing a project and/or thesis (bachelor, master) with me, feel free to contact me. If your interests don’t meet the suggested topics below but are related to my research, contact me as well and we’ll try to come up with a topic for your thesis.
Open master thesis topics
- Implementing a Recommender System Using a Cognitive Model on the Web: The aim of this thesis is to implement a computational cognitive model that explains behavior of users on the Web and to deploy this model for recommender systems. The model will be evaluated on well-known datasets from the research community and will be compared with other state-of-the art approaches. The algorithm should be implemented in Java or Python and there is the possibility to publish the results of the thesis in form of an academic paper together with the supervisors.
- Opinion Dynamics in Social Networks: The aim of this thesis is to build on our existing work, in which we studied the impact of social status on Opinion Dynamics and consensus building in Online collaboration networks. See http://www.know-center.tugraz.at/cms/wp-content/uploads/2015/08/ASONAM_2015_Paper.pdf for details. Specifically, within this thesis, the existing analysis should be extended to other types of networks. For the thesis, our open source framework for Opinion Dynamics can be used (Python, graph-tool) and extended. In case of relevant findings, there is the possibility to publish the results of the thesis in form of an academic paper together with the supervisors of the thesis.
- Tomislav Duricic (PhD thesis ongoing since 2016, expected to finish 2019). Behavior and Dynamics of Social Media and their impact on Cryptocurrency Markets (co-supervision with Univ. Prof. Stefanie Lindstaedt)
- Ilire Hasani-Mavriqi (PhD thesis ongoing since 2015, expected to finish 2018). Influence of Status on Consensus Building in Social Networks (co-supervision with Assoc. Prof. Denis Helic)
- Emanuel Lacic (PhD thesis ongoing since 2014, expected to finish 2018). Tackling Real-World Requirements in Recommender Systems (co-supervision with Univ. Prof. Stefanie Lindstaedt)
- Simone Kopeinik (2017). Applying Cognitive Learner Models for Recommender Systems in Small-Scale Learning Environments (PhD thesis, finished. Co-supervision with Univ. Prof. Stefanie Lindstaedt)
- Dominik Kowald (2017). Modeling Activation Processes in Human Memory to Improve Tag Recommendations (PhD thesis, finished. Co-supervision with Univ. Prof. Stefanie Lindstaedt)
- Muellner, P. (Master thesis ongoing since 2019). Music Recommender Systems.
- Wagner, M. (Master thesis ongoing since 2018). Mitigating bias and polarisation in social networks through recommendations.
- Reiter-Haas, M. (Master thesis ongoing since 2018). Job Recommender Systems.
- Riffert, T. (2019). Empirical analysis of political communities on Twitter (bachelor thesis, finished)
- Punz, A. (2016). Detection and Analysis of Communities on Twitter (bachelor thesis, finished)
- Müllner, P. (2016). Werkzeuge zur Analyse von Lerngruppen anhand derer Aktivitäten in einem sozialen Netzwerk (bachelor thesis, finished)
- Steinkellner, C. (2016). Empirical Analysis of Social Networks at a Scientific Conference (master thesis, finished)
- Feichtner, V. (2016). Information Quality in Wikipedia (master thesis, finished)
- Feichtner, V. (2016) Processing Large Edit Networks in Wikipedia (master project, finished)
- Duricic, T. (2015) Real-time recommendations using trust metrics and NoSQL databases, 2015. Cooperation via Erasmus+ programme together with University of Technology Zagreb, Croatia (master thesis, finished)
- Steinkellner, C. (2015). Empirical Analysis of Social Networks at a Scientific Conference (master project, finished)