di Sciascio Maria Cecilia, Brusilovsky Peter, Trattner Christoph, Veas Eduardo Enrique
2019
Information-seeking tasks with learning or investigative purposes are usually referred to as exploratory search. Exploratory search unfolds as a dynamic process where the user, amidst navigation, trial and error, and on-the-fly selections, gathers and organizes information (resources). A range of innovative interfaces with increased user control has been developed to support the exploratory search process. In this work, we present our attempt to increase the power of exploratory search interfaces by using ideas of social search—for instance, leveraging information left by past users of information systems. Social search technologies are highly popular today, especially for improving ranking. However, current approaches to social ranking do not allow users to decide to what extent social information should be taken into account for result ranking. This article presents an interface that integrates social search functionality into an exploratory search system in a user-controlled way that is consistent with the nature of exploratory search. The interface incorporates control features that allow the user to (i) express information needs by selecting keywords and (ii) to express preferences for incorporating social wisdom based on tag matching and user similarity. The interface promotes search transparency through color-coded stacked bars and rich tooltips. This work presents the full series of evaluations conducted to, first, assess the value of the social models in contexts independent to the user interface, in terms of objective and perceived accuracy. Then, in a study with the full-fledged system, we investigated system accuracy and subjective aspects with a structural model revealing that when users actively interacted with all of its control features, the hybrid system outperformed a baseline content-based–only tool and users were more satisfied.
Trattner Christoph, Kuśmierczyk Tomasz, Nørvåg Kjetil
2016
Trattner Christoph, Kowald Dominik, Seitlinger Paul, Ley Tobias
2016
Several successful tag recommendation mechanisms have been developed, including algorithms built upon Collaborative Filtering, Tensor Factorization, graph-based and simple "most popular tags" approaches. From an economic perspective, the latter approach has been convincing since calculating frequencies is computationally efficient and effective with respect to different recommender evaluation metrics. In this paper, we introduce a tag recommendation algorithm that mimics the way humans draw on items in their long-term memory in order to extend these conventional "most popular tags" approaches. Based on a theory of human memory, the approach estimates a tag's reuse probability as a function of usage frequency and recency in the user's past (base-level activation) as well as of the current semantic context (associative component).Using four real-world folksonomies gathered from bookmarks in BibSonomy, CiteULike, Delicious and Flickr, we show how refining frequency-based estimates by considering recency and semantic context 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 Collaborative Filtering, FolkRank and Pairwise Interaction Tensor Factorization with respect to recommender accuracy and runtime. We conclude that our approach provides an accurate and computationally efficient model of a user's temporal tagging behavior. Moreover, we demonstrate how effective principles of recommender systems can be designed and implemented if human memory processes are taken into account.
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.
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
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