Statement of Research

My main research topic is collection, organization and analysis of Big Data from social media using Machine Learning combined with Complex Networks.

I started my research career in 2012 with a publication in SocialCom 2012 regarding user privacy threats. This was the starting point of my PhD studies. Over the years my research interest have switched from security and social media (including crawling of social media [@nia2012a]) to the field of Machine Learning and Network Science, which have been my focus for the last three years.

From the social media data collected by my tool [@erlandsson2013a; @erlandsson2015a], social networks (that we are calling Social Interaction Networks [@nia2012a]) have been created and my last publications are addressing how to identify influential users in these networks using machine learning. In one of my most recent publication [@erlandsson2017a], I can show that it is possible to use data mining methods to identify seeds for information spreading models.

I also have a publication [@erlandsson2017b] addressing the challenge of how a smart sampling technique can be used to improve data collection from social media. This study have gained media attention and in mid April 2018 I did an interview with New York Times that showed interest in my research.

Although the network science field is quite new for me, I can really see the potential for me to make an impact here. With strong publications in both ways of identifying influential users and seeds for information cascade models.

The types of networks I’ve mostly been working with are multilayer networks created from Facebook data collected by my own crawler. This data is not traditional ego graphs but instead is the data based on users’ interactions on public groups. Hence have the networks been created by projecting user-to-posts interaction into user-to-user interaction.

Publications

Journals

Erlandsson, F., Bródka, P., Boldt, M., and Johnson, H. (2017). Do we really need to catch them all? A new User-guided Social Media Crawling method. Entropy 2017, 19(12):686, doi: 10.3390/e19120686.

Erlandsson, F., Bródka, P., Borg, A., and Johnson, H. (2016). Finding influential users in social media using association rule learning. Entropy 2016, 18(5):164, doi: 10.3390/e18050164.

Erlandsson, F., Nia, R., Johnson, H., and Wu, S. F. (2013). Making social interactions accessible in online social networks. Information Services and Use, 33(2):113– 117, doi: 10.3233/ISU-130702.

Conferences

Pham, P. D., Erlandsson, F., and Wu, S. F. “Social coordinates: A scalable embedding framework for online social networks”. In Complex Networks & Their Applications VI. COMPLEX NETWORKS 2017. Studies in Computational Intelligence, vol 689. Springer, Cham (2017), ICMLSC ’17, pages 191–196. ACM, DOI: doi: 10.1145/3036290.3036298.

Erlandsson, F., Nia, R., Boldt, M., Johnson, H., and Wu, S. F. (2015). Crawling Online Social Networks. In 2015 Second European Network Intelligence Conference (ENIC) (pp. 9-16). IEEE, doi: 10.1109/ENIC.2015.10.

Wang, T., Erlandsson, F., and Wu, S. F. (2015). Mining user deliberation and bias in online newsgroups: A dynamic view. In Proceedings of the 2015 ACM on Conference on Online Social Networks (pp. 209-219). ACM, doi: 10.1145/2817946.2817951.

Wang, T., Wang, K. C., Erlandsson, F., Wu, S. F., & Faris, R. (2013). The influence of feedback with different opinions on continued user participation in online newsgroups. In Proceedings of the 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (pp. 388-395). ACM, doi: 10.1145/2492517.2492555.

Nia, R., Erlandsson, F., Johnson, H., & Wu, S. F. (2013). Leveraging social interactions to suggest friends. In Proceedings of the 2013 IEEE 33rd International Conference on Distributed Computing Systems Workshops (pp. 386-391). IEEE, doi: 10.1109/icdcsw.2013.93.

Nia, R., Erlandsson, F., Bhattacharyya, P., Rahman, M. R., Johnson, H., & Wu, S. F. (2012). Sin: A platform to make interactions in social networks accessible. In Social Informatics (SocialInformatics), 2012 International Conference on (pp. 205-214). IEEE. doi: 10.1109/socialinformatics.2012.29.

Erlandsson, F., Boldt, M., & Johnson, H. (2012, September). Privacy threats related to user profiling in online social networks. In Privacy, Security, Risk and Trust (PASSAT), 2012 International Conference on and 2012 International Confernece on Social Computing (SocialCom) (pp. 838-842). IEEE. doi: 10.1109/socialcom-passat.2012.16).

Book chapters

Erlandsson, F., Brdóka, P., & Borg, A. (2017, November). Seed selection for information cascade in multilayer networks. In International Workshop on Complex Networks and their Applications (pp. 426-436). Springer, Cham. doi: 10.1007/978-3-319-28361-6_10.

Erlandsson, F., Borg, A., Johnson, H., & Bródka, P. (2016, January). Predicting user participation in social media. In International Conference and School on Network Science (pp. 126-135). Springer, Cham. doi: 10.1007/978-3-319-28361-6_10.

Books

Erlandsson, F. (2018). Human Interactions on Online Social Media: Collecting and Analyzing Social Interaction Networks. Karlskrona, Sweden: ISBN: 978-91-7295-344-4, urn:nbn:se:bth-15503. Doctoral thesis.

Erlandsson, F. (2105). On social interaction metrics: social network crawling based on interestingness. Karlskrona, Sweden: ISBN: 978-91-7295-287-4, urn:nbn:se:bth-00596 Licentiate Thesis.

Others

F. Erlandsson, P. Bródka, M. Boldt, and H. Johnson, (2018). Do We Really Need To Catch Them All? A New User-guided Social Media Crawling Method. International Conference on Computational Social Science IC2S2, Chicago, USA. extended abstract accepted for poster session.

Erlandsson F., Borg A., and Boldt M. (2018). Visualizing modus operandi similarity between burglaries in a city. NetCrime 2018 3nd Symposium on the Structure and Mobility of Crime, Paris, France, 2018, extended abstract.

Erlandsson F., Bródka P., M. Boldt, and H. Johnson, (2018). Do We Really Need To Catch Them All? A New User-guided Social Media Crawling Method”, NetSci 2018 International School and Conference on Network Science, Paris, France, extended abstract accepted for poster session

F. Erlandsson, P. Bródka, and A. Borg, (2018). Seed selection for information cascade in multilayer network”, NetSci 2018 International School and Conference on Network Science, Paris, France, extended abstract accepted for poster session.

Erlandsson, F, (2017). Replication Data for: Do We Really Need To Catch Them All? A New User-guided Social Media Crawling Method, Harvard Dataverse, V1, doi:10.7910/DVN/DCBDEP, UNF:6:rAWT7zGxHr6jKXil93DLXA==.