November 2012 Archives

Week 12 Readings (and media)

| 0 Comments | 0 TrackBacks

This week we will read one paper and discuss its application to your term projects and we will view two videos that focus on network analysis and its applications.

  • Lam, H.; Bertini, E.; Isenberg, P.; Plaisant, C.; Carpendale, S.; , "Empirical Studies in Information Visualization: Seven Scenarios," Visualization and Computer Graphics, IEEE Transactions on , vol.18, no.9, pp.1520-1536, Sept. 2012. Suggested by: Morteza {This paper considers a wide range of strategies for empirical study of information visualization. The focus is not explicitly on visual analytics, but you should be able to envision ways in which each strategy (scenario) can be applied or extended for application to visual analytics application.}.
  • http://vimeo.com/12941123 (22min) & http://www.spato.net/about/spato.mp4 (10 min) + the 1 page intro: http://rocs.northwestern.edu/projects/spato/spato.html. While not suggested by Josh, I've asked him to lead discussion on this pair of videos. {Each of which presents use of a tool that leverage advances in network science. Rather than reading a paper (other than the 1-page intro to one of the videos, the focus here will be on what you learn from the video (both have extensive narration, thus represent multimedia "short papers"). For the first video, if you want more detail, Beatrice suggested this paper (not required) that you might want to look at: Broeck, W., Gioannini, C., Goncalves, B., Quaggiotto, M., Colizza, V. and Vespignani, A. 2011: The GLEaMviz computational tool, a publicly available software to explore realistic epidemic spreading scenarios at the global scale. BMC Infectious Diseases 11, 37 + the site for the tool is worth a look: http://www.gleamviz.org/ )

Week 11 Readings

| 0 Comments | 0 TrackBacks

This week, there are again 3 relatively short papers to read and prepare to discuss.

  • Pak, A. and Paroubek, P. 2010: Twitter as a corpus for sentiment analysis and opinion mining. {This paper This paper deals with sentiment analysis of twitter data. It complements some recent papers we have read. As with those other papers, it does not apply visual analytics, so one focus of discussion should be on how it might do so}. Suggested by: Eun-Kyeong Kim
  • Boulos, M.N.K., Sanfilippo, A.P., Corley, C.D. and Wheeler, S. 2010: Social Web mining and exploitation for serious applications: Technosocial Predictive Analytics and related technologies for public health, environmental and national security surveillance. Computer Methods and Programs in Biomedicine 100, 16-23. {This paper, as the authors say "This paper explores Technosocial Predictive Analytics (TPA) and related methods for Web "data mining" where users' posts and queries are garnered from SocialWeb ("Web 2.0") tools such as blogs, micro-blogging and social networking sites to form coherent representations of real-time health events."}. Suggested by: Gloria Kim
  • Duckham, M. and Kulik, L. 2005: A formal model of obfuscation and negotiation for location privacy. Pervasive Computing, 243-251. {This paper addresses the issue of user privacy related to location-linked data in a formal way, tacking a computational approach to obfusction of a user's location while preserving the information required by a service. While the motivation was location-based services more than data captured from social media, similar issues exist across these domains.} Suggested by: Ryan Mullins

Week 10 Readings

| 0 Comments | 0 TrackBacks

This week, there are 3 relatively short papers to read and prepare to discuss.  The focus in two is on using twitter as data to answer questions and in the other on developing a visual analytics methods and demonstrating its application.  As you will see, two of the papers are about using twitter data to address empirical questions about human behavior, one is a visual analytics paper (not related to social media or social data). For the papers about using twitter data to answer questions, consider how methods from the visual analytics paper and/or other visual analytics papers we have read (particularly those from last week), might be adapted to the analytical tasks.

  • Crandall, D.J., Backstrom, L., Cosley, D., Suri, S., Huttenlocher, D. and Kleinberg, J. 2010: Inferring social ties from geographic coincidences. Proceedings of the National Academy of Sciences 107, 22436-22441. {This paper presents a statistical modeling-based approach to answering the question of whether proximity in time and space is evidence of social ties.  There is no visual analytics, but there is a clear space and time component to analysis and the potential for visual analytics to be applied.}.  Suggested by: Mo Yu
  • Paul, M.J. and Dredze, M. 2011: You are what you tweet: Analyzing Twitter for public health. Fifth International AAAI Conference on Weblogs and Social Media (ICWSM 2011).  {This paper focused on leveraging twitter as input to research and practice in public health. A specific focus is on what the authors call their Ailment Topic Aspect Model, which is used to create structured information from tweets that is applied to creating public health metrics.}. Suggested by: Beatrice Abiero
  • Sips, M., Kothur, P., Unger, A., Hege, H.-C. and Dransch, D. 2012: A Visual Analytics Approach to Multiscale Exploration of Environmental Time Series. IEEE VAST, Seattle: IEEE, 2899-2907. {This paper, just presented last week at IEEE VAST focuses on a new method for understanding temporal information.  The application domain is geographic, specifically environmental science; but the method has the potential to be broadly applicable}.  Suggested by:  Sam Stehle

Week 9 Readings

| 0 Comments | 0 TrackBacks

This week, there are 2 papers to read and prepare to discuss + 3 videos, all presented at IEEE VisWeek (2 in VAST sessions and 1 in an InfoVis session).  The focus is on different aspects of analyzing and using microblog data.  As noted above, the 3rd citation is just for reference for anyone who wants to follow up and actually read the paper out of interest or for design ideas.

  • Junghoon Chae,Dennis Thom, Harald Bosch, Yun Jang, Ross Maciejewski, David S. Ebert, Thomas Ertl (2012) Spatiotemporal Social Media Analytics for Abnormal Event Detection and Examination using Seasonal-Trend Decomposition, IEEE Transactions on Visualization and Computer Graphics, Vol. 18, No. 12, 143-152. {This paper is a follow up on the research that Dennis Thom presented for us. It adds some computational natural language processing methods and includes 3 case study applications. Be sure to watch the video.} 
  • Wenwen Dou, Xiaoyu Wang, Drew Skau, William Ribarsky, and Michelle X. Zhou (2012) LeadLine: Interactive Visual Analysis of Text Data through Event Identification and Exploration, IEEE Transactions on Visualization and Computer Graphics, Vol. 18, No. 12, 93-102. {This paper is complementary to the one above.  Its focus is more on events.  Be sure to watch the video.}
  • Nan Cao, Yu-Ru Lin, Xiaohua Sun, David Lazer, Shixia Liu, and Huamin Qu (2012) Whisper: Tracing the Spatiotemporal Process of Information Diffusion in Real Time, IEEE Transactions on Visualization and Computer Graphics, Vol. 18, No. 12, 2649-2658. {You do not need to read this paper - just watch the video that goes with it. I provide the paper in ANGEL and citation here for reference}

Week 8 Readings

| 0 Comments | 0 TrackBacks

This week, there are 2 papers.  The focus is on different aspects of analyzing and using microblog data.  The papers are ones suggested by students in the course.

  • Wakamiya, S., Lee, R. and Sumiya, K. 2012: Crowd-sourced urban life monitoring: urban area characterization based crowd behavioral patterns from Twitter. Proceedings of the 6th International Conference on Ubiquitous Information Management and Communication, Kuala Lumpur, Malaysia: ACM, 1-9.  {This article presents a model for a large-scale urban analytics with the location-based network to identify patterns in urban lifestyle in Japan with methods in visual analytics. The urban characteristics can be described by the temporal behavioral patterns collected from the crowd; Assoicated topic: (geo)VA and document retrieval/text analytics; Suggested by: YANG, JINLONG }
  • Mao, H., Shuai, X. and Kapadia, A. 2011: Loose tweets: an analysis of privacy leaks on twitter. Proceedings of the 10th annual ACM workshop on Privacy in the electronic society (WPES '11), Chicago, IL, USA: ACM, 1-12. {The authors discuss several types of privacy leaks (e.g. vacation plans, medical conditions) which may occur, unwittingly, through the use of Twitter. The authors then demonstrate these leaks by creating a classification script which detect the leaks through certain uses of language. Finally, the authors discuss who tends to leak information either about themselves or about others. The authors acknowledge that the purpose of their article is not to develop defensive measures related to privacy but rather to raise awareness about the extent of personal information leaks which may infringe on privacy. It is suggested that a similar classification system used by the authors may be employed as "guardian angel" systems to alert users when they may be divulging too much personal information. Suggested by: GLADFELTER, ANDREW}

Week 7 Readings

| 0 Comments | 0 TrackBacks

This week, there are 2 papers.  The focus is on different aspects of assessing success of visualization methods. This builds on last week's Perer & Shneiderman paper that presented the ideas of case studies (both short and long term) as one method of "evaluation."  This week's papers provide an overview of user-centered design and usability evaluation focused primarily on iterative development of a set of tools (the first) and a comparison of two strategies to evaluate a system once implemented (the second). 

  • Robinson, A.C. 2007: A design framework for exploratory geovisualization in epidemiology. Information Visualization 6, 197-214. {This paper is in the Sage database through the library. It focuses on work here to develop systematic methods to iteratively evaluate and refine exploratory visualization tools and to generate some design guidelines in the process. The tools evaluated in the comparison are visual without computational or statistical components, and Anthony does not call them visual analytics tools, although some of the results do discuss needs to link the visual methods with statistical methods. In reading this paper, think about whether/how the evaluation methods would apply to visual-statistical and/or visual-computational analysis tools that are possible to integrate in GeoViz Toolkit, PySal, NodeXL, R and related environments.}
  • North, C., Saraiya, P. and Duca, K. 2011: A comparison of benchmark task and insight evaluation methods for information visualization. Information Visualization 10, 162-181. {this paper has no geographic or social science component.  But, it provides a detailed comparison of two methods for formally evaluating a visualization tool that is designed to support insight. Either method could be applied to systems such as those your groups are planning to create/apply. The tool is primarily visual, thus the authors do not call it a visual analytics tools. So, while reading, consider how each method would differ if the tools being evaluated were visual-computational or visual-statistical ones.}

 

Week 6 Readings

| 0 Comments | 0 TrackBacks

·        Murray, A., Liu, Y., Rey, S. and Anselin, L. 2012: Exploring movement object patterns. The Annals of Regional Science 49, 471-484. {investigate Psysal: it is open source and has many capabilities: https://geodacenter.asu.edu/pysal  & http://code.google.com/p/pysal/ }

Perer, A. and Shneiderman, B. 2009: Integrating Statistics and Visualization for Exploratory Power: From Long-Term Case Studies to Design Guidelines. Computer Graphics and Applications, IEEE 29, 39-51. {investigate NodeXL - the outcome of this research; it is fairly powerful, and open source: http://nodexl.codeplex.com/}

Search This Blog

Full Text  Tag

Tag Cloud

Categories

Subscribe