Refine
Has Fulltext
- no (22)
Document Type
- Article (16)
- Monograph/Edited Volume (3)
- Other (3)
Is part of the Bibliography
- yes (22)
Keywords
- Bot Detection (1)
- Graph Convolutional Neural Networks (1)
- Graph Embedding (1)
- Social Media Analysis (1)
- activities (1)
- authentication (1)
- behavioral (1)
- collaborative learning (1)
- continuous (1)
- eLectures (1)
Institute
- Institut für Informatik und Computational Science (22) (remove)
We give a new view on building content clusters from page pair models. We measure the heuristic importance within every two pages by computing the distance of their accessed positions in usage sessions. We also compare our page pair models with the classical pair models used in information theories and natural language processing, and give different evaluation methods to build the reasonable content communities. And we finally interpret the advantages and disadvantages of our models from detailed experiment results
Design thinking research
(2012)
Design thinking research
(2011)
Design thinking research
(2012)
Beware of SMOMBIES
(2018)
Several research evaluated the user's style of walking for the verification of a claimed identity and showed high authentication accuracies in many settings. In this paper we present a system that successfully verifies a user's identity based on many real world smartphone placements and yet not regarded interactions while walking. Our contribution is the distinction of all considered activities into three distinct subsets and a specific one-class Support Vector Machine per subset. Using sensor data of 30 participants collected in a semi-supervised study approach, we prove that unsupervised verification is possible with very low false-acceptance and false-rejection rates. We furthermore show that these subsets can be distinguished with a high accuracy and demonstrate that this system can be deployed on off-the-shelf smartphones.
Tele-board : enabling efficient collaboration in digital design spaces across time and distance
(2011)
The use of video lectures in distance learning involves the two major problems of searchability and active user participation. In this paper, we promote the implementation and usage of a collaborative educational video annotation functionality to overcome these two challenges. Different use cases and requirements, as well as details of the implementation, are explained. Furthermore, we suggest more improvements to foster a culture of participation and an algorithm for the extraction of semantic data. Finally, evaluations in the form of user tests and questionnaires in a MOOC setting are presented. The results of the evaluation are promising, as they indicate not only that students perceive it as useful, but also that the learning effectiveness increases. The combination of personal lecture video annotations with a semantic topic map was also evaluated positively and will thus be investigated further, as will the implementation in a MOOC context.