2015
Fall detection is a classical use case for mobile phone sensing.Nonetheless, no open dataset exists that could be used totrain, test and compare fall detection algorithms.We present a dataset for mobile phone sensing-based fall detection.The dataset contains both accelerometer and gyroscopedata. Data were labelled with four types of falls(e.g., “stumbling”) and ten types of non-fall activities (e.g.,“sit down”). The dataset was collected with martial artistswho simulated falls. We used five different state-of-the-artAndroid smartphone models worn on the hip in a small bag.Due to the datasets properties of using multiple devices andbeing labelled with multiple fall- and non-fall categories, weargue that it is suitable to serve as benchmark dataset.
2015
Recent research has unveiled the importance of online social networks for improving the quality of recommender systems and encouraged the research community to investigate better ways of exploiting the social information for recommendations. To contribute to this sparse field of research, in this paper we exploit users’ interactions along three data sources (marketplace, social network and location-based) to assess their performance in a barely studied domain: recommending products and domains of interests (i.e., product categories) to people in an online marketplace environment. To that end we defined sets of content- and network-based user similarity features for each data source and studied them isolated using an user-based Collaborative Filtering (CF) approach and in combination via a hybrid recommender algorithm, to assess which one provides the best recommendation performance. Interestingly, in our experiments conducted on a rich dataset collected from SecondLife, a popular online virtual world, we found that recommenders relying on user similarity features obtained from the social network data clearly yielded the best results in terms of accuracy in case of predicting products, whereas the features obtained from the marketplace and location-based data sources also obtained very good results in case of predicting categories. This finding indicates that all three types of data sources are important and should be taken into account depending on the level of specialization of the recommendation task.
2015
We assume that recommender systems are more successful, when they are based on a thorough understanding of how people process information. In the current paper we test this assumption in the context of social tagging systems. Cognitive research on how people assign tags has shown that they draw on two interconnected levels of knowledge in their memory: on a conceptual level of semantic fields or LDA topics, and on a lexical level that turns patterns on the semantic level into words. Another strand of tagging research reveals a strong impact of time-dependent forgetting on users' tag choices, such that recently used tags have a higher probability being reused than "older" tags. In this paper, we align both strands by implementing a computational theory of human memory that integrates the two-level conception and the process of forgetting in form of a tag recommender. Furthermore, we test the approach in three large-scale social tagging datasets that are drawn from BibSonomy, CiteULike and Flickr. As expected, our results reveal a selective effect of time: forgetting is much more pronounced on the lexical level of tags. Second, an extensive evaluation based on this observation shows that a tag recommender interconnecting the semantic and lexical level based on a theory of human categorization and integrating time-dependent forgetting on the lexical level results in high accuracy predictions and outperforms other wellestablished algorithms, such as Collaborative Filtering, Pairwise Interaction Tensor Factorization, FolkRank and two alternative time-dependent approaches. We conclude that tag recommenders will benefit from going beyond the manifest level of word co-occurrences, and from including forgetting processes on the lexical level.
2015
In this paper, we introduce a tag recommendation algorithm that mimics the way humans draw on items in their long-term memory. Based on a theory of human memory, the approach estimates a tag's probability being applied by a particular user as a function of usage frequency and recency of the tag in the user's past. This probability is further refined by considering the in uence of the current semantic context of the user's tagging situation. Using three real-world folksonomies gathered from bookmarks in BibSonomy, CiteULike and Flickr, we show how refining frequency-based estimates by considering usage recency and contextual in uence outperforms conventional "most popular tags" approaches and another existing and very effective but less theory-driven, time-dependent recommendation mechanism. By combining our approach with a simple resource-specific frequency analysis, our algorithm outperforms other well-established algorithms, such as FolkRank, Pairwise Interaction Tensor Factorization and Collaborative Filtering. We conclude that our approach provides an accurate and computationally efficient model of a user's temporal tagging behavior. We demonstrate how effective principles of recommender systems can be designed and implemented if human memory processes are taken into account.
Tatzgern Markus, Grasset Raphael, Veas Eduardo Enrique, Schmalstieg Dieter
2015
Augmented reality (AR) enables users to retrieve additional information about real world objects and locations. Exploring such location-based information in AR requires physical movement to different viewpoints, which may be tiring and even infeasible when viewpoints are out of reach. In this paper, we present object-centric exploration techniques for handheld AR that allow users to access information freely using a virtual copy metaphor. We focus on the design of techniques that allow the exploration of large real world objects. We evaluated our interfaces in a series of studies in controlled conditions and compared them to a 3D map interface, which is a more common method for accessing location-based information. Based on our findings, we put forward design recommendations that should be considered by future generations of location-based AR browsers, 3D tourist guides or situated urban planning.
Parra Denis, Gomez M., Hutardo D., Wen X., Lin Yu-Ru, Trattner Christoph
2015
Twitter is often referred to as a backchannel for conferences. While the main conference takes place in a physicalsetting, on-site and off-site attendees socialize, introduce new ideas or broadcast information by microblogging on Twitter.In this paper we analyze scholars’ Twitter usage in 16 Computer Science conferences over a timespan of five years. Ourprimary finding is that over the years there are differences with respect to the uses of Twitter, with an increase ofinformational activity (retweets and URLs), and a decrease of conversational usage (replies and mentions), which alsoimpacts the network structure – meaning the amount of connected components – of the informational and conversationalnetworks. We also applied topic modeling over the tweets’ content and found that when clustering conferences accordingto their topics the resulting dendrogram clearly reveals the similarities and differences of the actual research interests ofthose events. Furthermore, we also analyzed the sentiment of tweets and found persistent differences among conferences.It also shows that some communities consistently express messages with higher levels of emotions while others do it in amore neutral manner. Finally, we investigated some features that can help predict future user participation in the onlineTwitter conference activity. By casting the problem as a classification task, we created a model that identifies factors thatcontribute to the continuing user participation. Our results have implications for research communities to implementstrategies for continuous and active participation among members. Moreover, our work reveals the potential for the useof information shared on Twitter in order to facilitate communication and cooperation among research communities, byproviding visibility to new resources or researchers from relevant but often little known research communities.
Kraker Peter
2015
In this paper, I present the evaluation of a novel knowledge domain visualization of educational technology. The interactive visualization is based on readership patterns in the online reference management system Mendeley. It comprises of 13 topic areas, spanning psychological, pedagogical, and methodological foundations, learning methods and technologies, and social and technological developments. The visualization was evaluated with (1) a qualitative comparison to knowledge domain visualizations based on citations, and (2) expert interviews. The results show that the co-readership visualization is a recent representation of pedagogical and psychological research in educational technology. Furthermore, the co-readership analysis covers more areas than comparable visualizations based on co-citation patterns. Areas related to computer science, however, are missing from the co-readership visualization and more research is needed to explore the interpretations of size and placement of research areas on the map.
Trattner Christoph, Steurer Michael
2015
Existing approaches to identify the tie strength between users involve typically only one type of network. To date, no studies exist that investigate the intensity of social relations and in particular partnership between users across social networks. To fill this gap in the literature, we studied over 50 social proximity features to detect the tie strength of users defined as partnership in two different types of networks: location-based and online social networks. We compared user pairs in terms of partners and non-partners and found significant differences between those users. Following these observations, we evaluated the social proximity of users via supervised and unsupervised learning approaches and establish that location-based social networks have a great potential for the identification of a partner relationship. In particular, we established that location-based social networks and correspondingly induced features based on events attended by users could identify partnership with 0.922 AUC, while online social network data had a classification power of 0.892 AUC. When utilizing data from both types of networks, a partnership could be identified to a great extent with 0.946 AUC. This article is relevant for engineers, researchers and teachers who are interested in social network analysis and mining.
Lin Yi-ling, Trattner Christoph, Brusilovsky Peter , He Daqing
2015
Crowdsourcing has been emerging to harvest social wisdom from thousands of volunteers to perform series of tasks online. However, little research has been devoted to exploring the impact of various factors such as the content of a resource or crowdsourcing interface design to user tagging behavior. While images’ titles and descriptions are frequently available in image digital libraries, it is not clear whether they should be displayed to crowdworkers engaged in tagging. This paper focuses on offering an insight to the curators of digital image libraries who face this dilemma by examining (i) how descriptions influence the user in his/her tagging behavior and (ii) how this relates to the (a) nature of the tags, (b) the emergent folksonomy, and (c) the findability of the images in the tagging system. We compared two different methods for collecting image tags from Amazon’s Mechanical Turk’s crowdworkers – with and without image descriptions. Several properties of generated tags were examined from different perspectives: diversity, specificity, reusability, quality, similarity, descriptiveness, etc. In addition, the study was carried out to examine the impact of image description on supporting users’ information seeking with a tag cloud interface. The results showed that the properties of tags are affected by the crowdsourcing approach. Tags from the “with description” condition are more diverse and more specific than tags from the “without description” condition, while the latter has a higher tag reuse rate. A user study also revealed that different tag sets provided different support for search. Tags produced “with description” shortened the path to the target results, while tags produced without description increased user success in the search task
Lex Elisabeth, Dennerlein Sebastian
2015
Today's complex scientific problems often require interdisciplinary, team-oriented approaches: the expertise of researchers from different disciplines is needed to collaboratively reach a solution. Interdisciplinary teams yet face many challenges such as differences in research practice, terminology, communication , and in the usage of tools. In this paper, we therefore study concrete mechanisms and tools of two real-world scientific projects with the aim to examine their efficacy and influence on interdisciplinary teamwork. For our study, we draw upon Bronstein's model of interdisciplinary collaboration. We found that it is key to use suitable environments for communication and collaboration, especially when teams are geographically distributed. Plus, the willingness to share (domain) knowledge is not a given and requires strong common goals and incentives. Besides, structural barriers such as financial aspects can hinder interdisciplinary work, especially in applied, industry funded research. Furthermore, we observed a kind of cold-start problem in interdisciplinary collaboration, when there is no work history and when the disciplines are rather different, e.g. in terms of wording. HowTo: Scientific Work in Interdisciplinary and Distributed Teams (PDF Download Available). Available from: https://www.researchgate.net/publication/282813815_HowTo_Scientific_Work_in_Interdisciplinary_and_Distributed_Teams [accessed Jul 13, 2017].
Kraker Peter, Schlögl C. , Jack K., Lindstaedt Stefanie
2015
Given the enormous amount of scientific knowledgethat is produced each and every day, the need for better waysof gaining – and keeping – an overview of research fields isbecoming more and more apparent. In a recent paper publishedin the Journal of Informetrics [1], we analyze the adequacy andapplicability of readership statistics recorded in social referencemanagement systems for creating such overviews. First, weinvestigated the distribution of subject areas in user librariesof educational technology researchers on Mendeley. The resultsshow that around 69% of the publications in an average userlibrary can be attributed to a single subject area. Then, we usedco-readership patterns to map the field of educational technology.The resulting knowledge domain visualization, based on the mostread publications in this field on Mendeley, reveals 13 topicareas of educational technology research. The visualization isa recent representation of the field: 80% of the publicationsincluded were published within ten years of data collection. Thecharacteristics of the readers, however, introduce certain biasesto the visualization. Knowledge domain visualizations based onreadership statistics are therefore multifaceted and timely, but itis important that the characteristics of the underlying sample aremade transparent.
Buschmann Katrin, Kasberger Stefan, Mayer Katja, Reckling Falk, Rieck Katharina, Vignoli Michela, Kraker Peter
2015
Insbesondere in den letzten zwei Jahren hat Österreichim Bereich Open Science, vor allem was Open Accessund Open Data betrifft, nennenswerte Fortschritte gemacht.Die Gründung des Open Access Networks Austria(OANA) und das Anfang 2014 gestartete Projekt e-InfrastructuresAustria können als wichtige Grundsteine fürden Ausbau einer österreichischen Open-Science-Landschaftgesehen werden. Auch das österreichische Kapitelder Open Knowledge Foundation leistet in den BereichenOpen Science Praxis- und Bewusstseinsbildung grundlegendeArbeit. Unter anderem bilden diese Initiativendie Grundlage für den Aufbau einer nationalen Open-Access-Strategie sowie einer ganz Österreich abdeckendenInfrastruktur für Open Access und Open (Research) Data.Dieser Beitrag gibt einen Überblick über diese und ähnlichenationale sowie lokale Open-Science-Projekte und-Initiativen und einen Ausblick in die mögliche Zukunftvon Open Science in Österreich.
Kraker Peter, Lindstaedt Stefanie , Schlögl C., Jack K.
2015
In this paper, we analyze the adequacy and applicability of readership statistics recorded in social reference management systems for creating knowledge domain visualizations. First, we investigate the distribution of subject areas in user libraries of educational technology researchers on Mendeley. The results show that around 69% of the publications in an average user library can be attributed to a single subject area. Then, we use co-readership patterns to map the field of educational technology. The resulting visualization prototype, based on the most read publications in this field on Mendeley, reveals 13 topic areas of educational technology research. The visualization is a recent representation of the field: 80% of the publications included were published within ten years of data collection. The characteristics of the readers, however, introduce certain biases to the visualization. Knowledge domain visualizations based on readership statistics are therefore multifaceted and timely, but it is important that the characteristics of the underlying sample are made transparent.
Mutlu Belgin, Veas Eduardo Enrique, Trattner Christoph
2015
Visualizations have a distinctive advantage when dealing with the information overload problem: since theyare grounded in basic visual cognition, many people understand them. However, creating the appropriaterepresentation requires specific expertise of the domain and underlying data. Our quest in this paper is tostudy methods to suggest appropriate visualizations autonomously. To be appropriate, a visualization hasto follow studied guidelines to find and distinguish patterns visually, and encode data therein. Thus, a visu-alization tells a story of the underlying data; yet, to be appropriate, it has to clearly represent those aspectsof the data the viewer is interested in. Which aspects of a visualization are important to the viewer? Canwe capture and use those aspects to recommend visualizations? This paper investigates strategies to recom-mend visualizations considering different aspects of user preferences. A multi-dimensional scale is used toestimate aspects of quality for charts for collaborative filtering. Alternatively, tag vectors describing chartsare used to recommend potentially interesting charts based on content. Finally, a hybrid approach combinesinformation on what a chart is about (tags) and how good it is (ratings). We present the design principlesbehindVizRec, our visual recommender. We describe its architecture, the data acquisition approach with acrowd sourced study, and the analysis of strategies for visualization recommendation