visualizing contextual and dynamic features of micropost streams

Visualizing Contextual and Dynamic Features of Micropost Streams

Alexander Hubmann-Haidvogel, Adrian M.P. Braşoveanu, Arno Scharl, Marta Sabou, Stefan Gindl

MODUL University Vienna Department of New Media Technology

Am Kahlenberg 1 1190 Vienna, Austria

{alexander.hubmann, adrian.brasoveanu, arno.scharl, marta.sabou, stefan.gindl}@modul.ac.at

ABSTRACT Visual techniques provide an intuitive way of making sense of the large amounts of microposts available from social media sources, particularly in the case of emerging topics of interest to a global audience, which often raise controversy among key stakeholders. Micropost streams are context-dependent and highly dynamic in nature. We describe a visual analytics platform to handle high-volume micropost streams from multiple social media channels. For each post we extract key contextual features such as location, topic and sentiment, and subsequently render the resulting multi-dimensional information space using a suite of coordinated views that support a variety of complex information seeking behaviors. We also describe three new visualization techniques that extend the original platform to account for the dynamic nature of micro-post streams through dynamic topography information landscapes, news flow diagrams and longitudinal cross-media analyses.

Categories and Subject Descriptors H.5.2 [Information Interfaces and Presentation]: User Interfaces – interaction styles. I.3.6. [Computer Graphics]: Methodology and Techniques – Interaction Technique.

General Terms Algorithms, Measurement, Design, Human Factors

Keywords Social Media Analytics, Microposts, Contextual Features, News Flow, Dynamic Visualization, Information Landscape

1. INTRODUCTION The ease of using social media channels has enabled people from around the world to express their opinions and propagate local or global news about virtually every imaginable topic. In doing so, they most often make use of short text messages (tweets, status updates) that we collectively refer to as microposts. Given the high volume, diversity and complex interdependency of social media-specific micropost streams, visual techniques play an in-creasingly important role in making sense of these novel data sources. Visual techniques can support analysts, journalists and

marketing managers alike in taking the pulse of public opinion, in understanding the perceptions and preferences of key stakehold-ers, in detecting controversies, and in measuring the impact and diffusion of public communications. This is particularly true for domains that pose challenges through their global reach, the com-peting interests of many different stakeholders, and the dynamic and often conflicting nature of relevant evidence sources (e.g., environmental issues, political campaigns, financial markets).

To support such scenarios across application domains, we have developed a (social) media monitoring platform with a particular focus on visual analytics (Hubmann, 2009). The platform enables detecting and tracking topics that are frequently mentioned in a given data sample (e.g., a collection of Web documents crawled from relevant sources). The advanced data mining techniques underlying the platform extract a variety of contextual features from the document space. A visual interface based on multiple coordinated views allows exploring the evolution of the document space along the dimensions defined by these contextual features (temporal, geographic, semantic, and affective), and subsequent drill-down functionalities to analyze details of the data itself. In essence, the platform has the key characteristics of a decision support system, namely: 1) it aggregates data from many diverse sources; 2) it offers an easy to use visual dashboard for observing global trends; 3) it allows both a quick drill-down and complex analyses along the dimensions of the extracted contextual fea-tures. We briefly report on the overall platform in Section 3.

The platform has been originally designed to analyze traditional news media, but from early 2011 we have adapted it to support micropost analysis, taking advantage of the robust infrastructure for crawling, analyzing and visualizing Web sources. The multi-dimensional analysis enabled by the original design of the portal is well suited for analyzing contextual features of microposts. However, the visualization metaphors did not properly capture the highly dynamic nature of micropost streams, nor did they allow cross-comparison between social and traditional media sources. Our latest research therefore focuses on novel methods to support temporal analysis and cross-media visualizations. In sections 4, 5 and 6 we describe these novel visualizations.

2. RELATED WORK With the rise of the social networks (Heer, 2005), understanding large-scale events through visualization emerged as an important research topic. Various visual interfaces have been designed for inspecting news or social media streams in diverse domains such as sports (Marcus, 2011), politics, (Diakopoulos, 2010; Shamma, 2009; Shamma, 2010), and climate change (Hubmann, 2009).

Copyright c© 2012 held by author(s)/owner(s).Published as part of the #MSM2012 Workshop proceedings,available online as CEUR Vol-838, at: http://ceur-ws.org/Vol-838#MSM2012, April 16, 2012, Lyon, France.

· #MSM2012 · 2nd Workshop on Making Sense of Microposts · 34

http://ceur-ws.org/Vol-838

http://ceur-ws.org/Vol-838

Researchers have emphasized different aspects of extracting useful information including (sub-)events (Adams, 2011), topics (Hubmann, 2009), and video fragments (Diakopoulos, 2011). Vox Civitas, for example, is a visual analytic tool that aims to support journalists in getting useful information from social media streams related to televised debates and speeches (Diakopoulos, 2010). In terms of the number and type of social media channels that are visualized, most approaches focus primarily on Twitter, while streams from Facebook and YouTube are visualized to a lesser extent (Marcus, 2010). We regard these three channels as equally important and visualize their combined content.

To reflect the dynamic nature of social media channels, some visualizations provide real-time updates displaying messages as they are published, and also projecting them onto a map – e.g., TwitterVision.com or AWorldofTweets.frogdesign.com. Given the computational overhead, however, real-time visualizations are the exception rather than the norm, since most projects rely on update times anywhere between a few minutes and a few days.

Visual techniques render microposts along dimensions derived from their contextual features. Most frequently, visualization rely on temporal and geographic features, but increasingly they exploit more complex characteristics such as the sentiment of the microp-ost, its content (e.g., expressed through relevant keywords), or characteristics of its author. Indeed, user clustering as seen in ThemeCrowds (Archambault, 2011) or geographical maps (e.g., (Marcus, 2011), TwitterReporter (Meyer, 2011)) are must-have features for every system that aims to understand local news and correlate them with global trends. Commercial services such as SocialMention.com and AlertRank.com use visualizations to track sentiment across tweets. During the 2010 U.S. Midterm Elections, sentiment visualizations have been present in all major media outlets from New York Times to Huffington Post (Peters, 2010).

Fully utilizing contextual features requires the use of appropriate visual metaphors. In general, social media visualizations rely on one of the following three visual metaphors:

Multiple Coordinated Views, also known as linked or tightly coupled views in the literature (Scharl, 2001), (Hubmann, 2009), ensures that a change in one of the views triggers an immediate update within the others. For example, the inter-face of Vox Civitas uses coordinated views to synchronize a timeline, a color-coded sentiment bar, a Twitter flow and a video window which helps linking parts of the video to rele-vant tweets (Diakopoulos, 2010). Additionally, (Marcus, 2011) use the multiple coordinated views in their system geared towards Twitter events and offer capabilities to drill down into sub-events and explore them based on geographic location, sentiment and link popularity.

Visual Backchannels (Dork, 2010) represent interactive interfaces synchronizing a topic stream (e.g., a video) with real-time social media streams and additional visualizations. This concept has evolved from the earlier concept of digital backchannel, referring to news media outlets supplementing their breaking news coverages with relevant tweets – e.g., during political debates or sport games (Shamma, 2010). However, additionally to the methods described in Hack the Debate (Shamma, 2009) and Statler (Shamma, 2010), tools that use the visual backchannel metaphor display not only the Twitter flow that corresponds to certain media events such as debates, but also a wealth of graphics and statistics.

Timelines follow the metaphor with the longest tradition, well suited for displaying the evolution of topics over time. Aigner et al. present an extensive collection of commented timelines (Aigner, 2011). The work by Adams et al. (Adams, 2011) is similar to our approach as it combines a color-coded sentiment display with interactive tooltips.

Beyond understanding micropost streams, a challenging research avenue compares the content of social media coverage with that of traditional news outlets. Cross-media analysis based on social sources is a relatively new field, but promising results have been published recently. In most cases comparisons are made between two sources such as Twitter and New York Times (Zhao, 2011), or Twitter and Yahoo! News (Hong, 2011). (Zhao, 2011) com-pares a Twitter corpus with a New York Times corpus to detect trending topics. For the New York Times, they apply a direct Latent Dirichlet Allocation (LDA), while for Twitter they use a modified LDA under the assumption that most tweets refer to a single topic. They use metrics including the distribution of catego-ries, breadth of topics coverage, opinion topic and the spread of topics through re-tweets, and show that most Twitter topics are not covered appropriately by traditional news media channels. They conclude that for spreading breaking world news, Twitter seems to be a better platform than a traditional medium such as New York Times. Hong et al. compare Twitter with Yahoo! News to understand temporal dynamics of news topics (Hong, 2011). They show that local topics do not appear as often in Twitter, and they go on to compare the performance of different models (LDA, Temporal Collection, etc). (Lin, 2011) conducts a study on media biasing on both social networks and news media outlets, but is focused only on the quantity of mentions. While these studies highlight differences between social and news media, they typi-cally lack visual support for monitoring diverse news sources.

3. ACQUISITION AND AGGREGATION OF CLIMATE CHANGE MICROPOSTS Climate Change is a global issue characterized by diverse opin-ions of different stakeholders. Understanding the key topics in this area, their global reach and the opinions voiced by different par-ties is a complex task that requires investigating how these dimen-sions relate to each other. The Media Watch on Climate Change portal (www.ecoresearch.net/climate) addresses this task by providing advanced analytical and visual methods to support different types of information seeking behavior such as browsing, trend monitoring, analysis and search.

The underlying technologies have originally been developed for monitoring traditional news media (Hubmann, 2009) and have recently been adapted for use with social media sources, in partic-ular micropost content harvested from Twitter, YouTube and Facebook. Between April 2011 and March 2012, the system has collected and analyzed an estimated 165,000 microposts from these channels. To support a detailed analysis of the collected microposts, we use a variety of visual metaphors to interact with contextual features along a number of dimensions: temporal, geographic, semantic and attitudinal. A key strength of the inter-face is the rapid synchronization of multiple coordinated views. It allows selecting the relevant data sources and provides trend charts, a document viewing panel as well as just-in-time infor-mation retrieval agents to retrieve similar documents in terms of either topic or geographic location. The right side of the interface contains a total of four different visualizations (two of which are being shown in Figure 1), which capture global views on the dataset. In addition to the shown semantic map (= information


lagcaeotefOCa

Tlyudthelyo

1

andscape; see Sgeographic map closed, maximizallow a more thoeven when placeon Climate Chanechnologies are

for example, forOceanic and AtmCancer Institute and Industry (see

The portal's visuyzing micropost

ular in the area odynamic charactherefore misses

events as they uny developing th

on the longitudin

1. The dynamextension ofcapturing thments in tinew microp

Section 4) and tand an ontology

zed, or opened orough inspectioed in different wnge focuses on e

currently beingr the Web intellmospheric Admi

(NCI), and thee www.weblyzar

ualizations provits along a varietyof climate changter of these ma key benefit o

nfold. To overcoe following set

nal and temporal

mic topography f the informationhe state of the ime, the topograosts are being pu

Figure 1. Sc

tag cloud, users y graph. Any of tin a separate pn (the views rem

windows). While environmental cog used for other ligence platforministration (NOA

e Vienna Chambrd.com).

ide a good startiy of contextual fe. The system d

micropost streamf social media –me this limitatioof novel visualianalysis of micr

information lan landscapes parnformation spacaphy is continuublished (Sectio

creenshot of the

can also selectthese views can bop-up window

main synchronizethe Media Watc

overage, the samdomains as we

ms of the NationAA), the Nationber of Commer

ing point for anfeatures, in parti

does not reflect thms, however, an– that of capturinon, we are currenizations that focropost streams:

andscapes are aradigm. Instead ce at discrete muously updated n 4).

e Media Watch

t a be to ed ch

me ell, nal nal ce

na-ic-he nd ng nt-us

an of

mo-as

2. Thsoter

3. Thofdathe

4. DYINFOInformanique ftories (mation We havtraditiomedia smation

For visis not arepresechangetations therefo

h on Climate Ch

he news flow diocial media chanrms of the topics

he cross-media f frequency and ata sources (e.g.e blogosphere; s

YNAMIC TORMATIONation Landscapefor conveying to(Krishnan, 2007landscapes onl

ave made use oonal news medisources and whelandscape at we

sualizing highly a satisfying solu

entation such ases in topical clus

lack the means tore no substitute

hange (www.eco

iagrams visualiznnels in real times that they menti

analysis charts sentiment for a

., between sociasee Section 6).

TOPOGRAN LANDSCes represent a p

opical relatednes7). Yet, the traly allows for vi

of such static laia, which were ere it was sufficeekly intervals.

dynamic microution. What is rs ThemeRiver (Hsters. Unfortunatto express compfor the informat

oresearch.net/cl

ze microposts froe, and reveal coion (Section 5).

allow longitudinany given topical media, news

PHY CAPE powerful visualiss in large documaditional concepisualizing staticandscapes when less dynamic

cient to recompu

opost streams, horequired insteadHavre, 2002) thtely, most of theplex topical relattion landscape m

limate)

om multiple rrelations in

nal analyses c and across

media, and

ization tech-ment reposi-pt of infor- conditions.

n visualizing than social

ute the infor-

owever, this d is a visual hat conveys

ese represen-tions and are

metaphor.


Ininrfgthrmdd

Mdptecsinin

5Wdcqtwnnbis(

1

Figure 2. Infor

n previous resenformation landelatedness and

formation landscgraphic map mhrough spatial epresenting agg

ments. As showdominant keywodocuments to fac

Micropost streamdecay of topics.posting. Dynamiectonic processe

cordingly. Risinshrinking hills a ng information nto a lower-dim

5. NEWS FWhile the dynamdepicts the evolucroposts withoutquire a comparatwo key problem

nating from multnance as well abetween them. Tssues by integratsee screenshot in

1. Falling barFacebook sinternally thits content, micropost isassociated kgenerates ofalling worddissolve intoin size accotheir respe“friends” inmentions ofcial media cthe populari

rmation landsca

earch, we have dscapes (Sabol et

rapidly changincapes are visualetaphor where proximity in th

glomerations (clun in Figure 2, trd labels (n-gram

cilitate the users'

ms are character. The topical stc information laes which modif

ng hills indicatefading of existinlandscapes, hig

ensional space.

FLOW DIAGmic topography ution of topic clt differentiating tive analysis of i

ms related to the tiple social medas the dynamic The News Flow Dting several visun Figure 3):

r graphs – Eastatus update, Yhrough the title o

and a list of ass posted we visukeywords throug

one falling wordds will "hit" the lo the correspond

ordingly. Figure ctive keyword

n the upper diagf a certain topicchannels and, thity of the topic i

ape on climate c

introduced dynt al., 2010) to adng data. Dynaml representationstopical relatedn

he visualization usters) of topicathe hills are labms) extracted froorientation.

rized by the raptructure changendscapes conveyfy the landscape the emergencng ones. In the pgh-dimensional

GRAM information lan

lusters within a their origin, so

individual microvisualization of

dia sources is to changes of top

Diagram concepual metaphors in

ch micropost (YouTube messagof the post, its tissociated keywoualize, in real-tigh falling wordd for each menlower part of theding keyword ba3 depicts how tbars (e.g., “e

gram). A keywor in microposts f

herefore, its heign the social med

change coverag

namic topographddress both topicic topography is based on a geness is conveye

space with hilally similar docbeled with sets om the underlyin

id emergence anes with each ney these changes

pe topography ae of new topic

process of generadata is projecte

ndscape metaphcollection of m

ome scenarios ropost streams. Thf microposts origshow their provpical associatiopt addresses theto a single displa

(Twitter messagge) is representeime of publishinords. When a neime, its respectivds. One documetioned topic. Th

e visualization anar, which increastopics fall towarexperiences” anrd bar collects afrom different s

ght correlates widia outlets that a

e

hy cal in-eo-ed lls

cu-of ng

nd ew as

ac-cs; at-ed

hor mi-re-he gi-ve-ns

ese ay

ge, ed

ng, ew ve

ent he nd ses ds nd all so-ith are

viye[B

2. MEaenple(Tcoshagdivleaca(n

3. Thdiapveasovticpetopon

Color-cto high

To demsame wing forsource 3a, “id“oxfamafter sesor”, th“oxfaminformaing theconnec

This viing varflow diimportaoccurrefalling over timacross lower a

sualized. The faears ago due to tBaer 2008].

Multi-source stacach falling wordnance or its assoe, uses the color

Twitter: gray, Faolor-coding is mhowing through ge of mentions ovidual media soast mentioned t

an be used to shnot shown in Figu

hreaded arcs. Wsplay to convey

ppear in the sameyed through shssociations, initiaver time. Relatece them. Figure eared seven timepics: “professor

nly displayed wh

coding is an imphlight various asp

Sentiment cothe sentiment

Source colostacked barssources in thFigure 3b, fhave three skeywords fro

Arc coloring relations betwfrequently), c

monstrate how aword (“ideas”) inr sentiment info(users can easi

deas” has a stronm”, but the wordeven hits, “ideashan with “respo

m”. Future versioation related to t

e importance of ctions over time.

isualization showrious visual metaiagrams to identant terms), to dence of terms ibars), and to sh

me (dynamic chavarious social

arcs).

alling bar metaphthe success of th

cked bars and cd is color-coded ociated sentimenr of the falling w

acebook: blue mmaintained in th

its diversely coof the correspondources. This allotopics across so

how sentiment vaure 3).

We use an adapy associations bme document. Difting arcs allowally displayed thd keywords are3b shows the to

es, co-occurs mr” and “responsehen we click on a

portant part of tpects of the data

oloring – the colt of a certain top

ring – words s with specific he stacked layoufor example, shources (Faceboo

om one source (Y

– we use darkertween the termsconnecting the m

associations evoln both diagramsormation, Figureily switch betwenger connectiond has only two s” has a strongeonse”, and alsoons of the visualthese connectioninteractivity and

wcases the poweaphors with colotify key topics (describe the rein a micropost how the evolutioanges in the distmedia sources

hor was quite pohe Digg Stack v

color-coded sentto represent eith

nt value. Figure 3words to reflect

marine, YouTubehe keyword barolored portions tding keyword wows inferring th

ources. The samalues instead of

ptation of the thbetween the keyDynamic link pw us to understahrough falling b

e highlighted to opic “ideas”, whost frequently we”. These threada keyword bar.

this visualization:

lor of the bars capic (see Figure 3

can also be dcolors that re

ut (provenance inhows a situationok, Twitter, YoYouTube) falling

r shades of gray s (i.e., they co-most related term

lve over time, ws: Figure 3a usee 3b for distingeen both modes

n with “responsehits. Figure 3b

er connection wo the same wealization module ns in the tooltipsd revealing the e

erful mechanismor-coding. We u(we only show tlations betweenare displayed

on of social medtribution of keywis represented

opular a few visualization

timent bars. her its prov-3, for exam-t their origin e: red). This rs, each bar the percent-

within the in-he most and

me metaphor f provenance

hreaded arcs ywords that atterns con-and how the bars, modify quickly no-

hich has ap-with the two ded arcs are

n. We use it

an represent a);

displayed as epresent the nformation); n where we ouTube) and g;

for stronger -occur more

ms.

we show the s color cod-guishing the s). In Figure e” than with b shows that with “profes-ak link with will include s, emphasiz-evolution of

m of combin-use the news the 50 most

n them (co-through the

dia coverage words/topics through the


6T(atheosth

Tizmmthntith

Bthimsc

Figure 3. N

6. CROSS-The Media Watci.e., monitoring

associated to a hese trend chart

either news mediof pre-computedsocial media strhey allow comp

To overcome thezation shown in

monitored over tmedia sources sehe interface (e.g

networks such asion makes use ohe portal to plot

By plotting topichat mention thampact of a topi

screenshot in Figcompares the am

News Flow Diag

MEDIA ANch on Climate Chover time) in tetopic and disag

ts are only plotteia or social medid topics. Therefeams where newaring across diff

ese limitations, wFigure 4, which

time and (b) monelected by clicking., traditional ns Twitter, YouTuof the data colleboth frequency

c frequency (i.eat topic) over tiic on different mgure 4 depicts a

mount of news co

gram with color

NALYSIS hange offers lonrms of topic freq

greement over aed over a singleia) and are availfore they are new topics emergferent media sou

we are developinh allows (a) definitoring this topng the appropria

news media outlube and Facebooction and chartinand sentiment re

e., number of doime, this visualimedia sources. query for the to

overage about the

r coding for sho

ngitudinal analysquency, sentimea topic. Howeve

data source (e.glable only for a seither suitable fge rapidly, nor durces.

ng the new visuaining a topic to bic across differe

ate check-boxes lets, blogs, sociok). The visualizng frameworks elated charts.

ocuments per daization shows thFor example, th

opic "durban" ane 17th Conferen

owing sentiment

sis ent er, g., set for do

al-be

ent in ial za-of

ay he he nd ce

of the PClimateNov toblogs, ence onthe covafter ththe newferenceost stre

In addithe doceither pumentstime. Tdifferenpositivecontrov"COP1gradualmedia the eve

t (Figure 3a, ab

Parties to the Ue Change (COP

o 31 Dec 2011 inand NGOs. Coin the 28th of Noverage of this tohe end of the evews media coverae has been far meams, except a sh

ition to frequenccuments mentionpositive or negas for a day or thThese charts helnt media outletse documents, wversies? A com7" in social ml shift from posisentiment rema

ent (see screensh

bove) and sourc

United Nations P17) held in Durn traditional newinciding with thovember, both sopic. The frequent, which is anage. It also show

more intense in nhort period of tim

cy charts, we alsning a specific tative documents,he standard devilp to understan, e.g., which out

which outlet is mparison of the media and news

itive to negativeained positive duhot in Figure 4).

ce (Figure 3b, b

Framework Corban, South Afriws media, Twitthe beginning of amples show an

uency then declin effect more prows that coveragenews media thanme in December

so visualize the stopic. A set of c, average sentimiation of the send the attitude etlet has the mostcharacterized baverage sentimmedia channel

e in microposts, uring the entire

elow).

nvention on ica, from 01 ter postings,

f the confer-n increase in ines sharply onounced in e of the con-n in microp-r.

sentiment of charts shows ment of doc-ntiment over expressed in t negative or by the most

ment towards s showed a while news duration of


Aisducthmle

Tatoaa2myadcc

7Inoooeaizitacsd

Wcinicsmm

Figure

An important isss the meaningfu

documents. The up the sentimencompute an overhen normalized

ment. This alloengths, such as n

The visualizationalso assist the usop terms associa

are calculated usand co-occurren2009), and are amatching the quyields the terms associated termsdisambiguation collected are alreclimate change d

7. CONCLUn this paper we

osts through visuon Climate Chanon visual analytextracting and viacteristic of the pzing micropost st enabled compl

and attitudinal dchange. Unlike msented approach data from multip

While the contecapitalized uponng another key cc nature. This i

scribed in this pmation landscapmajor topic clus

e 4. Cross-medi

sue of visualizinul computation sentiment detec

nt values of indrall sentiment vbased on the totws the comparnews articles and

n can not only trser in finding simated with the quing a combinatio

nce analysis onaggregated and uery term. A qu

"Durban", "UNs in Twitter miis not required eady pre-filtered

domain.

USION ANdescribe recent

ual means. Our nge portal (wwwtics over traditiisualizing a weaportal proved essstreams from thrlex analysis alondimensions in thmany other soc

relies on a roble social media o

extual nature of, the existing vicharacteristic of nitiated research

paper, includingpes, which showsters evolve; (ii)

a analysis for Nand

ng sentiment acrof sentiment va

ction algorithm cdividual words ivalue for the dotal number of torison of documd microposts.

rack user-specifimilar topics by puery term. Theseon of significantn the documenranked dependiuery for "COP1

NFCC" and "Cliicroposts. Addit

in this case, ad based on their

D OUTLOOwork on makingearlier work on

w.ecoresearch.neional news medalth of context fesential when adaree main social mng temporal, geohe challenging dial media visuabust infrastructuoutlets.

f the micropostisualizations fellf microposts, namh into the new

g: (i) dynamic tw through tecto) the news flow

November – Decaverage sentim

ross media outlealues for disparacumulatively adin a document

ocument, which okens in the doc

ments of differe

ied topics, but caproviding a list e associated termt phrases detectio

nt set (Hubmaning on documen17", for examplimate Change"tional query teras the documenr relevance to th

OK g sense of micro

the Media Watct/climate) focuse

dia and relied oeatures. This chaapting it to visuamedia channels, ographic, semantdomain of climalizations, the prure and combin

ts has been full short of convemely their dynamvisualizations d

topographic infoonic changes how diagrams whic

cember 2011; teent towards “C

ets ate dds

to is

cu-ent

an of

ms on

nn, nts le, as

rm nts he

op-ch ed on ar-al-as tic ate re-nes

lly ey-m-de-or-ow ch

enable streamsto eachdataset

Futurevisualizmicropextractiing ourof the related

Future and relpoint foevent odescribvariouswell suways othe com

8. ACKey covelopedTriple-Cby FITAgencytrian Cl

Adrian POSDRthe Minfinance

9. RE[Adams2011. Efacets. ConfereDecem

erm frequency COP17” (right).

a fine-graineds, showing key

h other; and (iii) s containing freq

work will focuszations to depict

posts. We are curing contextual fr current methodfeatures that weto interactive tim

research will allated to specific for narrative visuor a chain of evbe a chain of evs media channeluited for such anof incorporating mplex analytical

CKNOWLEomponents of thd within the DC (www.ecorese

T-IT Semantic Syy and the Austrilimate and Energ

Braşoveanu waRU/88/1.5/S/603nistry of Labor, ed by the Europe

EFERENCs, 2011] Brett Eventscapes: viIn MM '11 Pr

rence on Multimember 01, 2011), 1

distribution for

d, comparative topics being discross-media ana

quency and sent

s on feature extrt contextual andrrently working features from mds to the particule intend to intromelines and time

lso allow compaevents. We wil

ualizations (e.g.,vents; identifyinvents on social ls since our datan analysis. Finallg these individua

scenarios of dec

EDGMENThe system presenDIVINE (www.wearch.net/triple-cystems of the Auian Climate Resgy Fund (www.f

as partially supp370 (2009) on Family and Soci

ean Social Fund

ES Adams, Dinh

isualizing eventroceedings of thedia, Scottsdale477-1480.

r “Durban” (lef

analysis acrossscussed and howalysis based on iment informatio

raction from micd dynamic charaon more robust

microposts, by fularities of these oduce in future e series analysis

aring timelines all use timelines a, replaying the hng visual patter

media). We wasets and graphicly, we will invesal visualizationscision making to

TS nted in this papweblyzard.com/c) research projustrian Researchearch Program ffg.at; klimafond

ported by the str"Doctoral Schoial Protection, R– Investing in P

Phung, Svetha s over times w

he 19th ACM In, AZ, USA (Nov

ft)

s micropost w they relate longitudinal on.

croposts and acteristics of methods for

urther adapt-texts. Some releases are

s.

across topics as a starting history of an rns that best

will compare cal tools are stigate novel s to support ools.

per were de-/divine) and ects, funded h Promotion of the Aus-

ds.gv.at).

rategic grant olarships" of Romania, co-People.

Venkatesh. with emotive

nternational vember 28 -


[Aigner, 2011] Wolfgang Aigner, Silvia Miksch, Heidrun Schu-mann Christian Tominski. 2011. Visualization of Time-Oriented Data. Springer, 2011.

[Archambault, 2011] D. Archambault, D. Greene, P. Cunningham, and N. Hurley. ThemeCrowds: Multiresolution Summaries of Twitter Usage. In Proc. of the 3rd Workshop on Search and Min-ing User-generated Contents, Glasgow, UK, October 2011.

[Baer, 2008] K. Baer. Information Design Workbook. Graphic Approaches, Solutions and Inspiration + 30 Case Studies. Rock-port Publishers, 2008.

[Diakopoulos, 2010] N. Diakopoulos, M. Naaman, F. Kivran-swain. 2010. Diamonds in the Rough: Social Media Visual Ana-lytics for Journalistic Inquiry, IEEE Symposium on Visual Analyt-ics Science and Technology (VAST).

[Dork, 2010] Marian Dork, Daniel Gruen, Carey Williamson, and Sheelagh Carpendale. A visual backchannel for large-scale events. TVCG: Transactions on Visualization and Computer Graphics, 16(6):1129-1138, Nov/Dec 2010.

[Havre, 2002] Havre, S., Hetzler, E., Whitney, P., and Nowell, L.: ThemeRiver: Visualizing Thematic Changes in Large Document Collections. IEEE Transactions on Visualization and Computer Graphics, 8(1):9–20, 2002.

[Heer, 2005] J. Heer and D. Boyd. Vizster: Visualizing online social networks. In IEEE Symposium on Information Visualiza-tion, 2005.

[Hong, 2011] Liangjie Hong, Byron Dom, Siva Gurumurthy, Kostas Tsioutsiouliklis. 2011. A Time-Dependent Topic Model for Multiple Text Streams. KDD'11, August 21–24, 2011, San Diego, California, USA.

[Hubmann, 2009] Alexander Hubmann-Haidvogel, Arno Scharl, and Albert Weichselbraun. 2009. Multiple coordinated views for searching and navigating Web content repositories. Inf. Sci. 179, 12 (May 2009), 1813-1821.

[Krishnan, 2007] Krishnan, M., Bohn, S., Cowley, W., Crow, V., and Nieplocha, J. 2007. Scalable visual analytics of massive textual datasets. 21st IEEE International Parallel and Distributed Processing Symposium. IEEE Computer Society.

[Lin, 2011] Yu-Ru Lin, James P. Bagrow, David Lazer. 2011. More Voices Than Ever? Quantifying Media Bias in Networks. In: Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media, 2011.

[Marcus, 2011] Adam Marcus, Michael S. Bernstein, Osama Badar, David R. Karger, Samuel Madden, and Robert C. Miller. 2011. Twitinfo: aggregating and visualizing microblogs for event exploration. In Proceedings of the 2011 annual conference on Human factors in computing systems (CHI '11). ACM, New York, NY, USA, 227-236.

[Meyer, 2011] B. Meyer, K. Bryan, Y. Santos, Beomjin Kim. 2011. TwitterReporter: Breaking News Detection and Visualiza-tion through the Geo-Tagged Twitter Network. In: Proceedings of the ISCA 26th International Conference on Computers and Their Applications, March 23-15, 2011, Holiday Inn Downtown-Superdome, New Orleans, Louisiana, USA. ISCA 2011, 84-89.

[Peters, 2010] M. Peters. 2010. Four Ways to Visualize voter Sentiment for the Midterm Elections. Mashable Social Media. http://mashable.com/2010/10/29/elections-data-visualizations/.

[Sabol, 2010] Sabol, V., Syed, K.A.A., et al. 2010. Incremental Computation of Information Landscapes for Dynamic Web Inter-faces. 10th Brazilian Symposium on Human Factors in Computer Systems (IHC-2010). M.S. Silveira et al. Belo Horizonte, Brazil: Brazilian Computing Society: 205-208.

[Scharl, 2001] Scharl, A. 2001. Explanation and Exploration: Visualizing the Topology of Web Information Systems, Interna-tional Journal of Human-Computer Studies, 55(3): 239-258.

[Shamma, 2009] David A. Shamma, Lyndon Kennedy, Elizabeth F. Churchill. 2009. Tweet the Debates: Understanding Communi-ty Annotation of Uncollected Sources. In The first ACM SIGMM Workshop on Social Media (WSM 2009), October 23, 2009, Bei-jing, China.

[Shamma, 2010] David A. Shamma, Lyndon Kennedy, Elizabeth F. Churchill. 2010. Tweetgeist: Can the Twitter Timeline Reveal the Structure of Broadcast Events? In ACM Conference on Com-puter Supported Cooperative Work (CSCW 2010), February 6-10, 2010, Savannah, Georgia, USA.

[Zhao, 2011] Wayne Xin Zhao, Jing Jiang, Jianshu Weng, Jing He, Ee-Peng Lim, Hongfei Yan and Xiaoming Li. 2011. Compar-ing Twitter and Traditional Media using Topic Models. in Ad-vances in Information Retrieval - 33rd European Conference on IR Research, ECIR 2011, Dublin, Ireland, April 18-21, 2011. Proceedings. Lecture Notes in Computer Science 6611, Springer 2011, 338-349.


visualizing contextual and dynamic features of micropost streams

Documents