Showing posts with label Social network analysis. Show all posts
Showing posts with label Social network analysis. Show all posts

Saturday, April 12, 2014

AAG and Twitter

After spending a rather enjoyable few days at the Association of American Geographers (AAG) annual meeting in Tampa where there were some great talks on agent-based modeling, GIS and many other topics which I find interesting, along with catching up with some old friends and meeting new ones, its now time to head back up North. 

However, before jumping on the plane, I thought it would be intersing to look at the twitter traffic of the event (especially how there so many talks on using social media for geographical research). That being said, before showing the Twitter networks associated with the conference, one issue that was common among the conversion outside of the sessions was the lack of wifi access at the conference which accounts for small numbers of tweets durring the events but also one could argue people were more interested in the talks than that of tweeting. With that being said, within this analysis we show below we collected data using the #aag2014 and the @theAAG to explore the Twitter conversation.

The image below shows the # hashtag network from the conference with the biggest cluster being #aag2014 and associated words (click here to see a high solution image)


In the next image we removed the #aag2014 to only show the details of the network within this cluster. After removing the #aag2014 we re-ran the clustering on this network. The graph below shows the biggest clusters (with 3 or more nodes) within the #aag2014 group. Nicely outlined are the discussion topics (e.g. gender, sexuality, intimacy, climate, geoweb). Click here to see a higher resolution image.


Moving away from the hashtags and looking at the retweet network we were surprised to see that the AAG's account wasn't more active (click here to see a higher resolution image).


Also we are currently working on a spatial-temporal slider to look at the conversion over time. Below is a sneak peak from one moment in time. This will be soon coming to the Geosocial Gauge website. 



Tuesday, February 25, 2014

Geoinformatics and Social Media: A New Big Data Challenge

We recently contributed a chapter to "Big Data: Techniques and Technologies in Geoinformatics" entitled "Geoinformatics and Social Media: A New Big Data Challenge" where we explore how social media and ambient geographic information is transforming geoinformatics. We discuss the key characteristics of big geosocial data beofre moving onto geosocial complexity.  Specifically how goeosocial data is predominantly linked information; links are established among users to establish a social network and among words to define a storyline that is communicated through pieces of information. Aggregating all these connections (links) provides us with a view of the users as a structured, networked community that can be represented as a graph. We then turn to modeling and analyzing geosocial multimedia before concluding with an outlook pertaining to the grand challenges and opportunities for big geosocial data.



Full reference:
Croitoru, A., Crooks, A.T., Radzikowski, J., Stefanidis, A., Vatsavai, R. R. and Wayant, N. (2014), Geoinformatics and Social Media: A New Big Data Challenge, in Karimi, H. (ed.), Big Data Techniques and Technologies in Geoinformatics. CRC Press, Boca Raton, FL, pp. 207-232. (pdf)


Monday, October 21, 2013

IR: State-Driven and Citizen-Driven Networks

Our work exploring how social media can be used to study events around the world has resulted in a new publication in the  Social Science Computer Review entitled "International Relations: State-Driven and Citizen-Driven Networks." In essence what we are attempting to do is compare traditional international relations (e.g. from the United Nations General Assembly voting patterns) to those arising from the bottom up interactions (i.e from people on the ground). The abstract of the paper is below along with some of the images that accompany the paper.
The international community can be viewed as a set of networks, manifested through various transnational activities. The availability of longitudinal datasets such as international arms trades and United Nations General Assembly (UNGA) allows for the study of state-driven interactions over time. In parallel to this top-down approach, the recent emergence of social media is fostering a bottom-up and citizen driven avenue for international relations (IR). The comparison of these two network types offers a new lens to study the alignment between states and their people. This paper presents a network-driven approach to analyze communities as they are established through different forms of bottom-up (e.g. Twitter) and top-down (e.g. UNGA voting records and international arms trade records) IR. By constructing and comparing different network communities we were able to evaluate the similarities between state-driven and citizen-driven networks. In order to validate our approach we identified communities in UNGA voting records during and after the Cold War. Our approach showed that the similarity between UNGA communities during and after the Cold War was 0.55 and 0.81 respectively (in a 0-1 scale). To explore the state- versus citizen-driven interactions we focused on the recent events within Syria within Twitter over a sample period of one month. The analysis of these data show a clear misalignment (0.25) between citizen-formed international networks and the ones established by the Syrian government (e.g. through its UNGA voting patterns).


Full reference:
Crooks, A.T., Masad, D., Croitoru, A., Cotnoir, A., Stefanidis, A. and Radzikowski, J. (2013), International Relations: State-Driven and Citizen-Driven Networks, Social Science Computer Review. DOI:10.1177/0894439313506851
If you don't have access to Social Science Computer Review, send us an email and we can send you an early version of the paper. This is also only part of our work on using multiple networks to explore international relations. One can of course also explore the networks in more detail. For example in the figure below we plot the actual transfer of arms between states during the 2001 and 2011 period. One can clearly see how different states are connected with Syria however, Russia has connections to many states.

Arms transfers

Or if we explore Twitter hastags and add an edge between any pair of hashtags when they are used in the same tweet we can explore an emergent ontology of topic labels users associate with each other. For example, the #Allepo hashtag is associated with other hashtags which appear to local events, including “#civilian”, “#airstrike”, “#hunger”, “#pictures”, many of which are only connected to the #Aleppo hashtag as shown below.



Sunday, September 15, 2013

Geosocial Gauge Paper


As regular readers of the blog know, we have been spending a lot of time recently looking at social media and the growth in locational information within such media. To this end we are very happy to see one of our papers appear in the International Journal of Geographical Information Science. The paper is entitled "GeoSocial Gauge: A System Prototype for Knowledge Discovery from Social Media" which in essence discusses the challenge of merging diverse social media datasets into a single database which can then be used to generate geosocial knowledge. Below is the abstract:
"The remarkable success of online social media sites marks a shift in the way people connect and share information. Much of this information now contains some form of geographical content because of the proliferation of location-aware devices, thus fostering the emergence of geosocial media – a new type of user-generated geospatial information. Through geosocial media we are able, for the first time, to observe human activities in scales and resolutions that were so far unavailable. Furthermore, the wide spectrum of social media data and service types provides a multitude of perspectives on real-world activities and happenings, thus opening new frontiers in geosocial knowledge discovery. However, gleaning knowledge from geosocial media is a challenging task, as they tend to be unstructured and thematically diverse. To address these challenges, this article presents a system prototype for harvesting, processing, modeling, and integrating heterogeneous social media feeds towards the generation of geosocial knowledge. Our article addresses primarily two key components of this system prototype: a novel data model for heterogeneous social media feeds and a corresponding general system architecture. We present these key components and demonstrate their implementation in our system prototype, GeoSocial Gauge."

Full reference:
Croitoru, A., Crooks, A.T., Radzikowski, J. and Stefanidis, A. (in press), GeoSocial Gauge: A System Prototype for Knowledge Discovery from Social Media, International Journal of Geographical Information Science. DOI: 10.1080/13658816.2013.825724

If you don't have access to IGIS, send us an email and we can send you an early version of the paper.

Friday, May 10, 2013

Employment Growth through Labor Flow Network

    Omar Guerrero and Robert Axtell from the Department of Computational Social Science at GMU have recently published a paper in PLoS ONE entitled "Employment Growth through Labor Flow Networks." The work uses "newly available micro-data and the ability to work with large-scale, complex networks computationally, to study labor dynamics." Below is the abstract from the paper:

    It is conventional in labor economics to treat all workers who are seeking new jobs as belonging to a labor pool, and all firms that have job vacancies as an employer pool, and then match workers to jobs. Here we develop a new approach to study labor and firm dynamics. By combining the emerging science of networks with newly available employment micro-data, comprehensive at the level of whole countries, we are able to broadly characterize the process through which workers move between firms. Specifically, for each firm in an economy as a node in a graph, we draw edges between firms if a worker has migrated between them, possibly with a spell of unemployment in between. An economy's overall graph of firm-worker interactions is an object we call the labor flow network (LFN). This is the first study that characterizes a LFN for an entire economy. We explore the properties of this network, including its topology, its community structure, and its relationship to economic variables. It is shown that LFNs can be useful in identifying firms with high growth potential. We relate LFNs to other notions of high performance firms. Specifically, it is shown that fewer than 10% of firms account for nearly 90% of all employment growth. We conclude with a model in which empirically-salient LFNs emerge from the interaction of heterogeneous adaptive agents in a decentralized labor market.

      Communities of firms.

      To find more latest news from CSS check out our Facebook page.


      Tuesday, January 29, 2013

      New Paper: Demarcating New Boundaries

      We have just been informed that our paper entitled "Demarcating New Boundaries: Mapping Virtual Polycentric Communities through Social Media Content" has been accepted in Cartography and Geographic Information Science (CaGIS).

      A point density analysis revealing hotspots in geolocated tweets.

      The abstract for the paper is:
      The proliferation of social media has led to the emergence of a new type of geospatial information that defies the conventions of authoritative or volunteered geographic information, yet can be harvested to reveal unique and dynamic information about people and their activities. In this paper we address the identification and mapping of global virtual communities formed around issues of specific national interest. We refer to these connected virtual communities formed around issues related to a specific state as the polycentric virtual equivalent of that state. Identifying, mapping, and analyzing these virtual communities is a novel challenge for our community, and this is the subject we pursue in this paper. We present these communities relative to established conventions of statehood, address the harvesting of relevant geographical information from social media feeds, and discuss the challenge of visualizing such information. In order to do so we use the current geopolitical situation in Syria as a demonstrative example. 
      Below are some additional images from the paper.

      The user interface of our system prototype to harvest, map, and analyze streaming Twitter feeds. 

      A network representation of the polycentric virtual Syria as it is captured using Twitter feeds for the period July 10-17, 2012 using a population-normalized participation indices. The size of the nodes indicates level of participation in the corresponding model.



      Update 10th of May, 2013: Our paper is now out and made the front cover of Cartography and Geographic Information Science.

      Full reference: Stefanidis, A., Cotnoir, A., Croitoru, A., Crooks, A.T., Radzikowski, J. and Rice, M. (2013), Demarcating New Boundaries: Mapping Virtual Polycentric Communities through Social Media Content, Cartography and Geographic Information Science, 40(2): 116-129. (pdf)

      Thursday, October 18, 2012

      Research Update

      With the semester now well underway, I have been reflecting on some of the recent work we have been doing at George Mason University. This is currently taking two strands, the first being agent-based modeling and the second being deriving information from social media. Hopefully by the end of the semester, these two strands will be merged together.

      One of the models we are working on is the movement of people across national boarders. Below is a visualization of our work looking at the movment of people across the US/Mexico border which a specific focus on Arizona.


      Moreover, we have continued to work diseases and refugee camps. We are scaling up the model to represent the entire population of the Dadaab refugee camps along with verifying the model and exploring the spatial characteristics of the model (i.e the spread of cholera). If anyone will be at the annual North American Meetings of the Regional Science Association International in Ottowa  Canada feel free to come and listen to our presentation. The movie directly below shows the spread of cholera in one camp, while the second movie shows how cholera can be spread throughout the camps by people becoming infected and moving between the different camps.



      Some of this work has been feated in UPMagazine and Trajectory Magazine:

      Metcalfe, M. (2012), The Bounds of Rationality, UP Magazine, May, Issue 5: 40-43.
      Quinn, K. (2012), Visualizing the Invisible:GMU Pioneers a New Approach to Harvesting GEOINT, Trajectory Magazine, Fall, 11-12.

      Friday, January 27, 2012

      Social Media and the Emergence of Open-Source Geospatial Intelligence

      Sample of geolocated tweets referring
      Occupy Wall Street.
      We have just finished a paper entitled 'Social Media and the Emergence of Open-Source Geospatial Intelligence' for Socio-Cultural Dynamics and Global Security. For those interested below is the abstract:

      The emergence of social media has provided the public with an effective and irrepressible real-time mechanism to broadcast information. The great popularity of platforms such as twitter and YouTube, and the substantial amount of content that is communicated through them are making social media an essential component of open-source intelligence. The information communicated through such feeds conveys the interests and opinions of individuals, and reveals links and the complex structure of social networks. However, this information is only partially exploited if one does not consider its geographical aspect. Indeed, social media feeds more often than not have some sort of geographic content, as they may communicate the location from where a particular report is contributed, the geolocation of an image, or they may refer to a specific sociocultural hotspot. By harvesting this geographic content from social media feeds we can transfer the extracted knowledge from the amorphous cyberspace to the geographic space, and gain a unique understanding of the human lansdscape, its structure and organization, and its evolution over time. This new-found opportunity signals the emergence of open-source geospatial intelligence, whereby social media contributions can be analyzed and mined to gain unparalleled situational awareness. In this paper we showcase a number of sample applications that highlight the capabilities of harvesting geospatial intelligence from social media feeds, focusing particularly on twitter as a representative data source.
      Selection of geolocated pairs of tweeters and retweeters in Tokyo at the time immediately
      following the Sendai earthquake
      Full reference:
      Stefanidis, A., Crooks, A.T., Radzikowski, J., Croitoru, A. and Rice, M. (2014), Social Media and the Emergence of Open-Source Geospatial Intelligence, in Murdock, D.G., Tomes, R. and Tucker, C. (eds.), Human Geography: Socio-Cultural Dynamics and Global Security, US Geospatial Intelligence Foundation (USGIF), Herndon, VA, pp. 109-123. (pdf)

      Tuesday, December 6, 2011

      Harvesting ambient geospatial information from social media feeds

      A paper I  recently co-authored with Anthony Stefanidis and Jacek Radzikowski from George Mason University entitled "Harvesting ambient geospatial information from social media feeds" is now available in  GeoJournal. 
       
      The abstract for the paper reads as follows: "Social media generated from many individuals is playing a greater role in our daily lives and provides a unique opportunity to gain valuable insight on information flow and social networking within a society. Through data collection and analysis of its content, it supports a greater mapping and understanding of the evolving human landscape. The information disseminated through such media represents a deviation from volunteered geography, in the sense that it is not geographic information per se. Nevertheless, the message often has geographic footprints, for example, in the form of locations from where the tweets originate, or references in their content to geographic entities. We argue that such data conveys ambient geospatial information, capturing for example, people’s references to locations that represent momentary social hotspots. In this paper we address a framework to harvest such ambient geospatial information, and resulting hybrid capabilities to analyze it to support situational awareness as it relates to human activities. We argue that this emergence of ambient geospatial analysis represents a second step in the evolution of geospatial data availability, following on the heels of volunteered geographical information."

      Geolocating pairs of tweeters and retweeters