Autor*innen mit den meisten Dokumenten
Auflistung nach:
Neueste Veröffentlichungen
- ZeitschriftenartikelJazzFlow—Analyzing “Group Flow” Among Jazz Musicians Through “Honest Signals”(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Gloor, Peter A.; Oster, Daniel; Fischbach, KaiIn this project we aim to analyze “honest signals” between Jazz musicians by using sociometric badges with the goal of identifying structural properties of self-organizing creative teams. In particular, we are interested in the pre-requisites for “flow,” the state of work where “time flies,” and workers are at their most-productive best. We extend the concept of individual “flow” as defined by Csikszentmihalyi (Flow: the psychology of optimal experience. Harper Row, New York, 1990) to the group level (Sawyer in Group creativity: music, theater, collaboration. Psychology Press, Oxford, 2003; Group genius: the creative power of collaboration. Basic Books, New York, 2007), trying to identify some of the conditions indicative of the group flow state. We speculate that a band of Jazz musicians is particularly well suited to study group flow, because they are an archetype of a self-organizing creative team, involved in highly creatively work while passing leadership of the tune for the solo part from one band member to the next.
- ZeitschriftenartikelLearning to Discover Political Activism in the Twitterverse(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Finn, Samantha; Mustafaraj, EniWhen analysing social media conversations, in search of the public opinion about an unfolding political event that is being discussed in real-time (e.g., presidential debates, major speeches, etc.), it is important to distinguish between two groups of participants: political activists and the general public. To address this problem, we propose a supervised machine-learning approach, which uses inexpensively acquired labeled data from mono-thematic Twitter accounts to learn a binary classifier for the labels “political activist” and “general public”. While the classifier has a 92 % accuracy on individual tweets, when applied to the last 200 tweets from accounts of a set of 1000 Twitter users, it classifies accounts with a 97 % accuracy. Our work demonstrates that machine learning algorithms can play a critical role in improving the quality of social media analytics and understanding, whose importance is increasing as social media adoption becomes widespread.
- ZeitschriftenartikelInterview with Jim Hendler on Social Media and Collective Intelligence(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Metaxas, Panagiotis Takis
- ZeitschriftenartikelNews(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013)
- ZeitschriftenartikelSpecial Issue on Social Media(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Schoder, Detlef; Gloor, Peter A.; Metaxas, Panagiotis Takis
- ZeitschriftenartikelCan Computers Learn from the Aesthetic Wisdom of the Crowd?(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Bauckhage, Christian; Kersting, KristianThe social media revolution has led to an abundance of image and video data on the Internet. Since this data is typically annotated, rated, or commented upon by large communities, it provides new opportunities and challenges for computer vision. Social networking and content sharing sites seem to hold the key to the integration of context and semantics into image analysis. In this paper, we explore the use of social media in this regard. We present empirical results obtained on a set of 127,593 images with 3,741,176 tag assignments that were harvested from Flickr, a photo sharing site. We report on how users tag and rate photos and present an approach towards automatically recognizing the aesthetic appeal of images using confidence-based classifiers to alleviate effects due to ambiguously labeled data. Our results indicate that user generated content allows for learning about aesthetic appeal. In particular, established low-level image features seem to enable the recognition of beauty. A reliable recognition of unseemliness, on the other hand, appears to require more elaborate high-level analysis.
- ZeitschriftenartikelFrom Texts to Networks: Detecting and Managing the Impact of Methodological Choices for Extracting Network Data from Text Data(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Diesner, JanaThis thesis (Diesner in Technical Report CMU-ISR-12-101, 2012) addresses a series of methodological problems related to extracting information on socio-technical networks from natural language text data. Theories and models from the social sciences are leveraged and combined with computational approaches to (a) construct, analyze and compare network data and (b) combine text data and network data for analysis. This thesis entails various projects that serve three purposes: First, the impact of various common coding choices, including reference resolution and co-occurrence-based link formation, on network data and analysis results is empirically identified across multiple types of text data and domains. Second, different relation extraction methods are compared across various over-time, open-source, large-scale datasets with respect to the resulting network data and analysis results. This study offers a complement to traditional strategies for accuracy assessment. The relation extraction methods considered include network data construction based on (a) manually versus automatically built thesauri, (b) meta-data, and (c) collaboration with subject matter experts. Third, the concepts of grouping and roles from network analysis are integrated with text mining methods to enable the theoretically grounded, joint consideration of text data and network data for real-world applications.Overall, in this thesis, an interdisciplinary and computationally rigorous approach is used; thereby advancing the intersection of network analysis, natural language processing and computing. The contributions made with this work help people to utilize text data for network analysis, and to collect, manage and interpret rich network data at any scale. These steps are preconditions for asking substantive and graph-theoretic questions, testing hypotheses, and advancing theories about networks.
- ZeitschriftenartikelSolving Wicked Social Problems with Socio-computational Systems(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Introne, Joshua; Laubacher, Robert; Olson, Gary; Malone, ThomasGlobal climate change is one of the most challenging problems humanity has ever faced. Fortunately, a new way of solving large, complex problems has become possible in just the last decade or so. Examples like Wikipedia and Linux illustrate how the work of thousands of people can be combined in ways that would have been impossible only a few years ago. Inspired by systems like these, we developed the Climate CoLab—a global, on-line platform in which thousands of people around the world work together to create, analyze, and ultimately select detailed plans for what we humans can do about global climate change.The Climate CoLab has been operating since November 2009, and has an active community of thousands of users. In this article, we outline some of the challenges faced in developing the system, describe our current solutions to these problems, and report on our experiences.
- ZeitschriftenartikelSocial Media and Collective Intelligence—Ongoing and Future Research Streams(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Schoder, Detlef; Gloor, Peter A.; Metaxas, Panagiotis TakisThe tremendous growth in the use of Social Media has led to radical paradigm shifts in the ways we communicate, collaborate, consume, and create information. Our focus in this special issue is on the reciprocal interplay of Social Media and Collective Intelligence. We therefore discuss constituting attributes of Social Media and Collective Intelligence, and we structure the rapidly growing body of literature including adjacent research streams such as social network analysis, Web Science, and computational social science. We conclude by making propositions for future research where in particular the disciplines of artificial intelligence, computer science, and information systems can substantially contribute to the interdisciplinary academic discourse.
- ZeitschriftenartikelEditorial(KI - Künstliche Intelligenz: Vol. 27, No. 1, 2013) Klügl, F.