Showing papers by "Peter A. Gloor published in 2012"

Predicting Asset Value through Twitter Buzz

Abstract: This paper describes early work trying to predict financial market movement such as gold price, crude oil price, currency exchange rates and stock market indicators by analyzing Twitter posts. We collected Twitter feeds for 5 months obtaining a large set of emotional retweets originating from within the US, from which six public opinion time series containing the keywords “dollar% t ”, “$% t ”, “gold% t ”, “oil% t , “job% t ” and “economy% t ” were extracted. Our results show that these variables are correlated to and even predictive of the financial market movement. Except “$% t ”, all other five public opinion time series are identified by a Granger-causal relationship with certain market movements. It is demonstrated that daily changes in the volume of economic topic retweeting seem to match the value shift occurring in the corresponding market next day.

Measuring social capital in creative teams through sociometric sensors

Abstract: We describe the results of an experiment capturing the face-to-face ‘honest signals’ of knowledge workers through sociometric badges. We find that collective creativity of teams is a function of the aggregated social capital of members. The higher it is, the higher their creative output. We collected communication data of 14 graduate students and their instructor during a one-week seminar, comparing it against the creative output of their teamwork. As a second component of social capital we also measured the level of trust team members show to each other through surveys. We find that the more team members directly interact with each other face-to-face, and the more they trust other team members, the more creative and of higher quality the result of their teamwork is.

Wikimaps: dynamic maps of knowledge

Abstract: We introduce Wikimaps, a tool to create a dynamic map of knowledge from Wikipedia contents. Wikimaps visualise the evolution of links over time between articles in different subject areas. This visualisation allows users to learn about the context a subject is embedded in, and offers them the opportunity to explore related topics that might not have been obvious. Watching a Wikimap movie permits users to observe the evolution of a topic over time. We also introduce two static variants of Wikimaps that focus on particular aspects of Wikipedia: latest news and people pages. ‘Who-works-with-whom-on-Wikipedia’ (W5) links between two articles are constructed if the same editor has worked on both articles. W5 links are an excellent way to create maps of the most recent news. PeopleMaps only include links between Wikipedia pages about ‘living people’. PeopleMaps in different-language Wikipedias illustrate the difference in emphasis on politics, entertainment, arts and sports in different cultures.

Tracking the 2011 Student-led Collective Movement in Chile through Social Media Use

Abstract: Using social media archives of the 2011 Chilean student unrest and dynamic social network analysis, we study how leaders and participants use social media such as Twitter, and the Web to self-organize and communicate with each other, and thus generate one of the biggest "smart movements" in the history of Chile. In this paper we i) describe the basic network topology of the 2011 student-led social movement in Chile; ii) explore how the student leaders are connected to, and how are they seen by (a) political leaders, and (b) University authorities; iii) hypothesize about key success factors and risk variables for the Student Network Movement's organization process and sustainability over time. We contend that this social media enabled massive movement is yet another manifestation of the network era, which leverages agents' socio-technical networks, and thus accelerates how agents coordinate, mobilize resources and enact collective intelligence.

Proceedings of the First ACM International Workshop on Hot Topics on Interdisciplinary Social Networks Research

Abstract: With the blessing of information technology, we are living in an increasingly networked world. People, information and other entities are connected via World Wide Web, email networks, instant messaging networks, mobile communication networks, online social networks, etc. These online networks grow fast and possess huge amount of recorded information, which presents great opportunities in understanding the science of these networks, and in developing new applications from these networks and for these networks. The increasingly networked society has fundamentally changed our way of thinking, individual behaviors and social activities. It is foreseen that the public health relating to epidemic diseases is greatly impacted by this emerging connectivity as they are by nature mediated by direct or indirect human interactions and mobility. However, new challenges have to be met --- the networks are huge and information is noisy, and they demand new methodologies in accessing and analyzing these networks, and in developing theories and applications for the networks. To meet with these challenges, researchers from a wide range of academic fields, including theory and algorithms, data mining and machine learning, computer systems and networks, statistical physics and complex systems, sociology, social psychology, economics and managerial science, etc. are all actively studying various aspects concerning social and information networks. However, we lack the proper opportunities for people from these diverse backgrounds to directly interact with each other. The diversity of approaches and methodologies to study various social networks has raised the need for an interdisciplinary effort to create the required expertise to address the fundamental open questions in this field. This workshop is intended to present such an opportunity and serve as a forum to bring together people from various fields to exchange their latest research results and to sparkle new ideas and directions to properly understand these networks. It will be held on August 12, 2012, in conjunction with ACM KDD 2012, August 12-16, Beijing, China.

Supporting development efforts of clinical care teams

Abstract: This paper describes the results of a longitudinal study of team communication structure for two distinct interdisciplinary healthcare teams at a large academic children medical centre in the USA. Our goal was to inform teams of opportunities and strategies that strengthen their communication structure. To this purpose we proposed an operational framework based on four steps: observation, measurement, mirroring and design. We analysed the e-mail archives of two teams to monitor structural changes in e-mail communication over one year. Since the first analyses, both teams were designated as strategic priorities by the institution, underwent off site meetings to define and put into execution a strategic plan, initiated processes to improve care delivery and reviewed the results of the initial social network analysis. We found that for both teams the communication network improved over time showing a higher cohesiveness, an increase in density, network resilience and external connectivity.

Galaxysearch -discovering the knowledge of many by using wikipedia as a meta-searchindex

Abstract: We propose a dynamic map of knowledge generated from Wikipedia pages and the Web URLs contained therein. GalaxySearch provides answers to the questions we don’t know how to ask, by constructing a semantic network of the most relevant pages in Wikipedia related to a search term. This search graph is constructed based on the Wikipedia bidirectional link structure, the most recent edits on the pages, the importance of the page, and the article quality; search results are then ranked by the centrality of their network position. GalaxySearch provides the results in three related ways: (1) WikiSearch - identifying the most prominent Wikipedia pages and Weblinks for a chosen topic, (2) WikiMap - creating a visual temporal map of the changes in the semantic network generated by the search results over the lifetime of the returned Wikipedia articles, and (3) WikiPulse - finding the most recent and most relevant changes and updates about a topic.

Forecasting social movements by web buzz analysis

Abstract: Widespread Internet usage has led to the availability of a cacophony of fact, fiction and opinion composed by all elements of society; events such as the recent panic in Veracruz, Mexico over Twitter chatter of a violent attack on a school demonstrates the societal power of this cacophony. Governments, news organizations and most importantly individuals produce data that represents a stream of consciousness of society, albeit a stream with many competing voices, agendas, and noise. Embedded in this stream are the opinions and activities that will move society and make news.

Wikipulse - Automatically Generating an Online Newspaper from Wikipedia Articles

Abstract: More and more, user-generated content is complementing conventional journalism. While we don’t think that CNN or New York Times and its professional journalists will disappear anytime soon, formidable competition is emerging through humble Wikipedia editors. In earlier work (Becker 2012), we found that entertainment and sports news appeared on average about two hours earlier on Wikipedia than on CNN and Reuters online. In this project we build a news-reader that automatically identifies late-breaking news among the most recent Wikipedia articles and then displays it on a dedicated Web site.