Digital Forces - Social: Future Trends, Student Projects Highlight, Software and More

DigitalForces– Social:FutureTrends,StudentProjectsHighlight,Software,

andMore

TCSiON FacultyDevelopmentProgrammeSept7,2016

PonnurangamKumaraguru(“PK”)AssociateProfessor

ACMDistinguishedSpeakerfb/ponnurangam.kumaraguru,@ponguru

WhoamI?

� AssociateProfessor,IIIT-Delhi� Ph.D.fromSchoolofComputerScience,

CarnegieMellonUniversity(CMU)� Researchinterests-Privacy,e-crime,onlinesocialmedia,andusablesecurity

� FoundingHead,CERC@IIITD� Co-ordinateandmanagePrecog,precog.iiitd.edu.in

� ACMDistinguishedSpeaker

2

https://www.youtube.com/channel/UCHWDvGDh4QjWbV79bM2neSg

3

4

Whatwedabblewith!

5

6

OSMPenetrationinIndia

7

8

4/5V’sofOnlineSocialMedia

9

V

Non-trustworthyContent

FAKE

10

$

RUMORS

Methodology

11

TrainingData

� 500Tweetsperevent� UsedCrowdFlower

12

Event Tweets UsersBostonMarathonBlasts(2013) 7,888,374 3,677,531

Typhoon Haiyan /Yolanda(2013) 671,918 368,269

CyclonePhailin (2013) 76,136 34,776

WashingtonNavy yard shootings (2013) 484,609 257,682

Polarvortex cold wave (2014) 143,959 116,141

OklahomaTornadoes (2013) 809,154 542,049

Total 10,074,150 4,996,448

CredibilityModeling

13

Featureset Features (45)

Tweetmeta-dataNumberofsecondssincethetweet;Sourceoftweet(mobile/web/etc);Tweetcontainsgeo-coordinates

Tweetcontent(simple)

Numberofcharacters;Numberofwords;NumberofURLs;Numberofhashtags;Numberofuniquecharacters;Presenceofstocksymbol;Presenceofhappysmiley;Presenceofsadsmiley;Tweetcontains`via';Presenceofcolonsymbol

Tweetcontent(linguistic)

Presenceofswearwords;Presenceofnegativeemotionwords;Presenceofpositiveemotionwords;Presenceofpronouns;Mentionofselfwords intweet(I;my;mine)

Tweetauthor Numberoffollowers;friends;timesincetheuserifonTwitter;etc.

TweetnetworkNumberofretweets;Numberofmentions;Tweetisareply;Tweet isaretweet

Tweet links WOTscorefortheURL;Ratiooflikes/dislikesforaYouTubevideo

Implementation

FeedbackbyUsers

15

v

Harvard(1839)– Harvard– Harvard– Harvard– MIT–Northwestern– UIUC– WUSL– CMU(2009)– IIITD(2015)

17

http://twitdigest.iiitd.edu.in/TweetCred/

18

De-duplicatingaudience

Socialaudience=437,632+153,000+805,097orless??

19

Challenges

20

ProfessionalOpinion

Dating

HeterogeneousOSNs

Personal

DegreeofDetails

QualityanddescriptivepersonalAndprofessionalinformation

Little personalinformationDescriptiveopinions

AttributeEvolution

Time

Informationevolvedononebutnotonother

{jainpari,Bangalore}

RegistrationwithsameinformationonbothOSNs{paridhij,NewDelhi}

GenericIdentityResolution

21

Extractavailable&

discriminativefeatures

CandidateIdentities

IDENTITYSEARCH IDENTITYLINKING

PairwiseComparisons

HeuristicIdentitySearch

22cerc.iiitd.ac.in

Profile

Content

Self-mention

Network Syntactic and Image

Search Linking

If self-identified / returned by

more than one search method

No

Yes

Candidate Identities

name, location,usernamemobile no,

post,friends,

followers

ParidhiJain,Ponnurangam Kumaraguru,andAnupam Joshi.2013.@Iseek‘fb.me’:IdentifyingUsersacrossMultipleOnlineSocialNetworks.InProceedingsofthe22ndInternationalConferenceonWorldWideWeb,WWW’13Companion.ACM,NewYork,NY,USA,1259- 1268.DOI=http://dx.doi.org/10.1145/2487788.2488160[HonorableMentionAward}

Harvard(1839)– Harvard– Harvard– Harvard– MIT–Northwestern– UIUC– WUSL– CMU(2009)– IIITD(2016)

23

OSNforPolicing

24

TopOfficialsalsoonTwitter

25

InterestingHashtags Strikeaconversation

ProblemStatement

� Designingtechnologytosupportcommunicativeandcollaborativepolicinginurbancommunitiesleveragingonlinesocialmediaasaplatform

26

Methodology

� Interviewusingmulti-stakeholderapproach

27

Citizens Police

• 17Interviews• 204Survey

• 20Interviews• 445Surveys

InterviewAnalysis(Groundtheory)

28

WhyOSN:WhatarethewayspolicecanuseOSNtomaintainlawandorder?HowcancitizenshelppoliceusingOSN?

Increasecitizenvolunteerstoreportcrime.Reducecommunicationgap/engagebetter.ImproveCoordination.

PreferredOSNplatform:WhichOSNwillpoliceandcitizensliketouseformaintaininglawandorder?WhichOSNismostusefulandhelpful forlawandorderpurposes?

Amongofficersonly.Withcitizens.

Targetaudience:WhoisthetargetaudienceforpoliceonOSNforbuilding intelligence,stayingconnected,broadcastinginformation?(nosubcategories)Challengesandlimitations:AretheresomehindranceswhichstoptheuseofOSNasaneffectivetoolformaintaining lawandorder?Whataccordingtoyouarethemajorhindrances?Whatdoyouthinkcangowrong?Anyexample?

Meaningfulinformation.Verifytheinformation.Acknowledgecitizen’smessages.Needtechnicalteamsandguidelines

Citizenvolunteers– Increasehumanresource

� Involvecitizenvolunteerstoidentifyoffenders- Findtrafficdefaulters

- Neighborhoodcrimereporters

29

“DelhiTrafficPolicepageinvolves publicinfindingtrafficviolators, onthebasisofwhichchallans (fine)areissued.Soourlimitedresourcesareincreasedandwecancatchmanymorepeoplebyseekinghelpofpublic.”

ByP17

ByP7

“OSNhashelpedintraffic management,introducedgoodtrafficpractices, samecanbedonefor[other]crimessuchasviolenceorpropertyfraud.OSNcanbeusedtocreateacommunity ofpeoplewhowillbeusingit(OSN)[toidentifycrime].“

“IfIseeagirlinavulnerablesituation Imightgivethisinformation, andthey[Police]cantakeinstantaction.”

ByC7

ReduceCommunicationGap� UnderstandCitizenOpinion

� ProvidesAnonymity� Useoffakeprofiles

� Complainaboutcrimeagainstinfluentialpeople

� Citizensfortheirownsafetyshouldnotinformthepolicethroughpublicpostswithsensitivecontent.

30

“Suppose,wewanttoformanopinionaboutatopicinthatcasewecangetalotofinformation fromdifferentpeople.Wecanformanopinion/makepolicydecisions[basedontheseopinions].“ ByP1

QuantifyActionableInformation

WhetherOSNcansupportpolicetogetactionable informationaboutcrimeand

residents’opinionaboutpolicingactivities inurbancitiesofIndia.

31

Methodology:DataCollection

32

1600commentson255posts

Posts&Comments

Filtered

Collectedpublicposts,21July- 21Aug2014

UnderstandingVictimization

Word #

Fear 7

Worried 6

Concerned 8

Noticeof 13

Issue 22

Trouble 4

33

Accountability

34

WordTreevisualizationsofpostsinwhichresidentsquestioned policeusingthewordwhy.

35

36

HowmanyofyouhavepostedmobilenumbersonOnlineSocial

Networks?

Howmanyofyouhaveseenmobilenumbersbeingpostedon

OnlineSocialNetworks?

Sampleposts

37

Sampleposts

38

Sampleposts

39

Sampleposts

40

Datastatistics

� Twitter:12thOctober2012– 20thOctober2013� Facebook: 16thNovember2012– 20thApril2013

41

Numbers Category+91 Category0 Categoryvoid Total

Twitter Facebook Twitter Facebook Twitter Facebook Twitter Facebook

MobileNumbers

885 2,191 14,909 8,873 25,566 25,294 41,360 36,358

Userprofiles

1,074 2,663 17,913 9,028 31,149 25,406 49,817 36,588

42

SocialCallerApp

43

https://play.google.com/store/apps/details?id=com.ayush.socialcaller&hl=en

44

20Interviews 4FGDs

10,427Surveys

#privacyindia12Methodology

18months!

0.08

7.73

0.14

7.101.10

6.88

0.28

8.14

1.96

8.58

0.52

0.21

0.74

3.19

9.38

0.350.03

0.04

0.25

2.94

11.290.02

8.57

0.05

9.39

9.530.21

0.17

9.390.48

0.020.03

0.010.08

Sample

Demographics

Gender(N=10,232)Male 67.57Female 32.43

46

Age(N=10,350)<18 1.5418-24 21.3125-29 32.2030-39 25.9040-49 14.0950-64 4.4665+ 0.50

Age

Internet&SocialMediaWhatdoyoufeelaboutprivacyofyourpersonalinformationonyourOSN?

47

Q42,N=6,855ItisnotaconcernatallSinceIhavespecifiedmyprivacysettings,mydataissecurefromaprivacybreachEventhough,Ihavespecifiedmyprivacysettings,IamconcernedaboutprivacyofmydataItisaconcern,butIstillsharepersonalinformationItisaconcern;henceIdonotsharepersonaldataonOSN


48

Q42,N=6,855ItisnotaconcernatallSinceIhavespecifiedmyprivacysettings,mydataissecurefromaprivacybreach 42.13Eventhough,Ihavespecifiedmyprivacysettings,IamconcernedaboutprivacyofmydataItisaconcern,butIstillsharepersonalinformationItisaconcern;henceIdonotsharepersonaldataonOSN


49

Q42,N=6,855Itisnotaconcernatall 19.30SinceIhavespecifiedmyprivacysettings,mydataissecurefromaprivacybreach 42.13Eventhough,Ihavespecifiedmyprivacysettings,Iamconcernedaboutprivacyofmydata 23.84Itisaconcern,butIstillsharepersonalinformation 8.02Itisaconcern;henceIdonotsharepersonaldataonOSN 6.71

Internet&SocialMediaIfyoureceiveafriendshiprequestonyourmostfrequentlyusedOSN,whichofthefollowingpeoplewillyouaddasfriends?

50

Q43,N=6,929PersonofoppositegenderPeoplefrommyhometownPersonwithniceprofilepictureStrangers(peopleyoudonotknow)Somebody,whomyoudonotknoworrecognizebuthavemutual/commonfriendswithAnyone


51

Q43,N=6,929PersonofoppositegenderPeoplefrommyhometownPersonwithniceprofilepicture 10.12Strangers(peopleyoudonotknow)Somebody,whomyoudonotknoworrecognizebuthavemutual/commonfriendswithAnyone


52

Q43,N=6,929Personofoppositegender 27.39PeoplefrommyhometownPersonwithniceprofilepicture 10.12Strangers(peopleyoudonotknow)Somebody,whomyoudonotknoworrecognizebuthavemutual/commonfriendswithAnyone 2.99


53

Q43,N=6,929Personofoppositegender 27.39Peoplefrommyhometown 19.51Personwithniceprofilepicture 10.12Strangers(peopleyoudonotknow) 4.99Somebody,whomyoudonotknoworrecognizebuthavemutual/commonfriendswith 8.31Anyone 2.99

54

http://precog.iiitd.edu.in/research/privacyindia/

Takeaways

� OnlineSocialMediaisadifferentbeastintermsofprivacy,identity,andcredibility-Research/technologiesshouldbedeveloped

�Multipleinterestingresearch,engineering,andinnovationwaitingtobedone

� Iaminterestedincollaborating/interactingwithfacultyandresearchersinterestedintheseandtopicsaroundthese

55

StudentProjects

� EvaluatereputationonOSM�Measureinformationdiffusion� Trust&Credibility� Privacy� SocialNetworkAnalysis� e-crime� Policing� Identityresolution

56

TeachingMethods

� OnlineDiscussions� Problemsolving� Projects� Challengingexams/quizzes�…

57

58

http://precog.iiitd.edu.in/

59

Thankyou!

[email protected]

Digital Forces - Social: Future Trends, Student Projects Highlight, Software and More

Technology