Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Designing and Evaluating Techniques to
 Mitigate Misinformation Spread on 
Micro-blogging Web Services

1,002 views

Published on

Designing and Evaluating Techniques to
 Mitigate Misinformation Spread on 
Micro-blogging Web Services

- Aditi Gupta Ph.D. Thesis, July 2015

Published in: Education
  • Be the first to comment

  • Be the first to like this

Designing and Evaluating Techniques to
 Mitigate Misinformation Spread on 
Micro-blogging Web Services

  1. 1. Designing and Evaluating Techniques to 
 Mitigate Misinformation Spread on 
 Micro-blogging Web Services" Adi$  Gupta     Under  the  Supervision  of  Dr.  Ponnurangam  Kumaraguru   Indraprastha  Ins9tute  of  Informa9on  Technology,  Delhi   July  6,  2015  
  2. 2. Power of Social Media" 2   300  hours  of   video  uploaded   every  minute   500  million   tweets  posted   every  day   1.44  Billion   monthly  ac$ve   users   60  million   photos  shared   everyday   *  2015  Sta9s9cs    
  3. 3. Real World Events" 3  
  4. 4. Misinformation on Social Media" 4  
  5. 5. Misinformation on Social Media" 5  
  6. 6. Misinformation on Social Media" 6  
  7. 7. Focus: Twitter" 7   Profile   Photo   Hashtag   Followers   Retweet  BuOon   Username  
  8. 8. Misinformation Tweets" FAKE   RUMORS   8   $  
  9. 9. Aim"      Designing  and  Evalua9ng  Techniques  to     Mi9gate  Misinforma9on  Spread  on     Micro-­‐blogging  Web  Services   9  
  10. 10. Proposed Solution" 10   –  Learning  to  Rank  model  for  assessing  credibility  of  Tweets   –  Model  based  on  ground  truth  data  for  20  real  world  events   and  45  features     –  System  evalua9on  using  year  long  real  world  experiment   –  1800+  users  requested  for  credibility  score  of  more  than        14.2  million  tweets.    
  11. 11. TweetCred Demo"
  12. 12. Approach" 12   Characterizing   Misinforma$on   and  Fake  Content     Ranking   Framework  to   Assess  Credibility   Building  and   Evalua$ng  a  Real-­‐ $me  System     Detec9ng  fake  images   (Hurricane  sandy)     Analyzing  rumor   propaga9on  (Boston   blasts)     Detec9ng  user   communi9es  (three   events)     Analyzing  rumors  spread   in  India  centric  events   (Mumbai  blasts  and   Assam  riots)   14  events  data  tagging     30%  of  tweets  provide   informa9on  (17%   credible  informa9on     Linear  logis9c  regression     Present  ranking   algorithm  to  assess   credibility  in  tweets   using  pseudo  relevance   feedback   45  features  computable   for  a  single  tweet     Live  deployment:  1,800+   TwiOer  users       Credibility  score   computed  for  14+   Million  tweets     Evaluated  TweetCred  in   terms  of  response  9me,   effec9veness  and   usability  
  13. 13. Data Collection" – Created  a  24*7  data  collec9on  framework   - Streaming  /  REST  APIs   - JSON  Format   - MySql  Databases     – Collected  2+  Billion  tweets  from  2011-­‐14   13  
  14. 14. Approach" 14   Characterizing   Misinforma$on   and  Fake  Content     Ranking   Framework  to   Assess  Credibility   Building  and   Evalua$ng  a  Real-­‐ $me  System     Detec9ng  fake  images   (Hurricane  sandy)     Analyzing  rumor   propaga9on  (Boston   blasts)     Detec9ng  user   communi9es  (three   events)     Analyzing  rumors  spread   in  India  centric  events   (Mumbai  blasts  and   Assam  riots)   14  events  data  tagging     30%  of  tweets  provide   informa9on  (17%   credible  informa9on     Linear  logis9c  regression     Present  ranking   algorithm  to  assess   credibility  in  tweets   using  pseudo  relevance   feedback   45  features  computable   for  a  single  tweet     Live  deployment:  1,800+   TwiOer  users       Credibility  score   computed  for  14+   Million  tweets     Evaluated  TweetCred  in   terms  of  response  9me,   effec9veness  and   usability  
  15. 15. Background: Hurricane Sandy" – Dates:  Oct  22-­‐  31,  2012   – Damages  worth  $75  billion   – Coast  of  NE  America   15   Faking  Sandy:  Characterizing  and  Iden9fying  Fake  Images  on  TwiOer  during  Hurricane  Sandy.  Adi9  Gupta,  Hemank  Lamba,   Ponnurangam  Kumaraguru  and  Anupam  Joshi.  Accepted  at  the  2nd  Interna9onal  Workshop  on  Privacy  and  Security  in  Online   Social  Media  (PSOSM),  in  conjunc9on  with  the  22th  Interna9onal  World  Wide  Web  Conference  (WWW),  Rio  De  Janeiro,   Brazil,  2013.  Best  Paper  Award.  
  16. 16. Fake Image Tweets" 16  
  17. 17. Data Description" 17   Total  tweets   1,782,526   Total  unique  users   1,174,266   Tweets  with  URLs   622,860   Tweets  with  fake  images   10,350   Users  with  fake  images   10,215   Tweets  with  real  images   5,767   Users  with  real  images   5,678  
  18. 18. Network Analysis" 18     Tweet  –  Retweet  graph  for  the  propaga9on  of  fake  images  during  first  2  hours   Node  -­‐>  User  Id   Edge  -­‐>  Retweet      
  19. 19. Role of Twitter Network" –  Analyzed  role  of  follower  network  in  fake  image   propaga9on   –  Crawled  the  TwiOer  network  for  all  users  who   tweeted  the  fake  image  URLs   19   –  Graph  1   -  Nodes:  Users,    Edges:  Retweets   –  Graph  2   -  Nodes:  Users,    Edges:  Follow  rela9onships  
  20. 20. Results" 20   Total  edges  in  retweet  network   10,508   Total  edges  in  follower-­‐followee  network   10,799,122   Common  edges   1,215   %age  Overlap   11%  
  21. 21. Classification"    5  fold  cross  valida9on   21   Tweet  Features  [F2]   Length  of  Tweet   Number  of  Words   Contains  Ques9on  Mark?   Contains  Exclama9on  Mark?   Number  of  Ques9on  Marks   Number  of  Exclama9on  Marks   Contains  Happy  Emo9con   Contains  Sad  Emo9con   Contains  First  Order  Pronoun   Contains  Second  Order  Pronoun   Contains  Third  Order  Pronoun   Number  of  uppercase  characters   Number  of  nega9ve  sen9ment  words   Number  of  posi9ve  sen9ment  words   Number  of  men9ons   Number  of  hashtags   Number  of  URLs   Retweet  count   User  Features  [F1]   Number  of  Friends   Number  of  Followers   Follower-­‐Friend  Ra9o   Number  of  9mes  listed   User  has  a  URL   User  is  a  verified  user   Age  of  user  account  
  22. 22. Classification Results" 22   F1  (user)   F2  (tweet)   F1+F2   Naïve  Bayes   56.32%   91.97%   91.52%   Decision  Tree   53.24%   97.65%   96.65%   •  Best  results  were  obtained  from  Decision  Tree  classifier,  we  got  97%   accuracy  in  predic9ng  fake  images  from  real.     •  Tweet  based  features  are  very  effec9ve  in  dis9nguishing  fake  images  tweets   from  real,  while  the  performance  of  user  based  features  was  very  poor.      
  23. 23. Boston Blasts" –  Twin  blasts  occurred  during  the  Boston  Marathon   -  April  15th,  2013  at  18:50  GMT   –  3  people  were  killed  and  264  were  injured   –  First  Image  on  TwiOer  (within  4  mins)     23   $1.00  per  RT  #BostonMarathon  #PrayForBoston:  Analyzing  Fake  Content  on  TwiOer.  Adi9  Gupta,  Hemank  Lamba  and   Ponnurangam  Kumaraguru.  Accepted  at  IEEE  APWG  eCrime  Research  Summit  (eCRS),  San  Francisco,  USA,  2013.  
  24. 24. Sample Fake Tweets" 24   >  50,000  RTs   >  30,000  RTs  
  25. 25. Data Description" Total tweets 7,888,374 Total users 3,677,531 Time of the blast Mon Apr 15 18:50 2013 Time of first tweet Mon Apr 15 18:53 2013 25  
  26. 26. Geo-Located Tweets" 26  
  27. 27. Identifying Rumor / True tweets" –  Tagged  most  viral  20  tweet  content   -  Rumor  /  Fake   -  True   -  Generic  (NA)     –  Six  Rumors   -  130,690  Tweets  /  Retweets  (29%)   -  R.I.P.  to  the  8  year-­‐old  boy  who  died  in  Boston’s  explosions,  while   running  for  the  Sandy  Hook  kids.  #prayforboston     –  Seven  True  news   -  116,454  Tweets  /  Retweets  (20%)   -  Doctors:  bombs  contained  pellets,  shrapnel  and  nails  that  hit  vicGms   #BostonMarathon  @NBC6     –  Seven  Generic   -  206,816  Tweets  /  Retweets  (51%)   -  #PrayForBoston    
  28. 28. Fake Content User Profiles" Account  1   Account  2   Account  3   Account  4   No.  of  Followers   10   297   249   73,657   Profile  Crea$on  Date   Mar  24  2013   Apr  15  2013   Feb  07  2013     Dec  04  2008   Total  No.  of  Statuses   2   2   294   7,411   No.  of  Fake  Tweets   2   2   1   1   Current  Status   Suspended   Suspended   Suspended    Ac9ve   28   Username:  BostonMarathons  
  29. 29. Temporal Patterns" 29   Fake  content  /  rumors  becomes  viral  in  first  7-­‐8  hours  just  aoer  the  event.      
  30. 30. Tweet Source Analysis" 30   76%   16%   8%   Fake   64%   31%   5%   True   51%  41%   8%   General   Mobile   Web   Others  
  31. 31. Spread of Fake Content" –  Using  linear  regression   –  Predict  how  viral  a  rumor  would  get   -  Based  on  aOributes  of  users  who  are  propaga9ng  the  rumor   –  Based  on:   -  Follower   -  Friends   -  Favorited     -  Status   -  Verified     31  
  32. 32. Predicting Spread of Fake Content" 32   Results  show  it  is  possible  to  predict  how  viral  a  rumor  would  become  in   future  based  on  aOributes  of  users  currently  propaga9ng  the  rumor.  
  33. 33. Book & Media" 33  
  34. 34. Approach" 34   Characterizing   Misinforma$on   and  Fake  Content     Ranking   Framework  to   Assess  Credibility   Building  and   Evalua$ng  a  Real-­‐ $me  System     Detec9ng  fake  images   (Hurricane  sandy)     Analyzing  rumor   propaga9on  (Boston   blasts)     Detec9ng  user   communi9es  (three   events)     Analyzing  rumors  spread   in  India  centric  events   (Mumbai  blasts  and   Assam  riots)   14  events  data  tagging     30%  of  tweets  provide   informa9on  (17%   credible  informa9on     Linear  logis9c  regression     Present  ranking   algorithm  to  assess   credibility  in  tweets   using  pseudo  relevance   feedback   45  features  computable   for  a  single  tweet     Live  deployment:  1,800+   TwiOer  users       Credibility  score   computed  for  14+   Million  tweets     Evaluated  TweetCred  in   terms  of  response  9me,   effec9veness  and   usability   Credibility  Ranking  of  Tweets  during  High  Impact  Events.  Adi9  Gupta  and  Ponnurangam  Kumaraguru,  Workshop  on  Privacy   and  Security  on  Online  Social  Media  (PSOSM),  co-­‐located  with  the  21st  Interna9onal  World  Wide  Web  Conference  (WWW),   Lyon,  France,  2012.  
  35. 35. Tweets about an Event" 35   Tweets   #event   Informa$on   No   informa$on   Tweets   with   informa$on   Credible   Informa$on   Non-­‐ Credible   Informa$on   Fake  news  /  Rumors    Personal  Opinions  /   Spam   No.  of  people  affected   Place  of  event   Pictures  /  videos          
  36. 36. 36  
  37. 37. Architecture" 37  
  38. 38. Data Statistics" Events Tweets Trending Topics UK Riots 542,685 #ukriots, #londonri- ots, #prayforlondon Libya Crisis 389,506 libya, tripoli Earthquake in Virginia 277,604 #earthquake, Earth- quake in SF JanLokPal Bill Agitation 182,692 Anna Hazare, #jan- lokpal, #anna Apple CEO Steve Jobs resigns 158,816 Steve Jobs, Tim Cook, Apple CEO US Downgrading 148,047 S&P, AAA to AA Hurricane Irene 90,237 Hurricane Irene, Tropical Storm Irene Google acquires Motorola Mobility 68,527 Google, Motorola Mobility News of the World Scandal 67,602 Rupert Murdoch, #murdoch Abercrombie & Fitch stocks drop 54,763 Abercrombie & Fitch, A&F Muppets Bert and Ernie were gay 52,401 Bert and Ernie Indiana State Fair Tragedy 49,924 Indiana State Fair Mumbai Blast, 2011 32,156 #mumbaiblast, Dadar, #needhelp New Facebook Messenger 28,206 Facebook Messenger 38  
  39. 39. Annotation" –  Step  1   -  R1.  Contains  informa9on  about  the  event   -  R2.  Is  related  to  the  event,  but  contains  no  informa9on   -  R3.  Not  related  to  the  event   -  R4.  Skip  tweet     –  Step  2   -  C1.  Definitely  credible   -  C2.  Seems  credible   -  C3.  Definitely  incredible   -  C4.  Skip  tweet.         39  
  40. 40. Annotation Results" 40   –  Each  tweet  annotated  by  3  people     –  Inter-­‐annotator  agreement  (Cronbach  Alpha)  =  0.748     –  30%  of  tweets  provide  informa9on  (17%  credible   informa9on)  and  14%  was  spam  
  41. 41. Feature Sets" 41   Message based features Length of the tweet Number of words Number of unique characters Number of hashtags Number of retweets Number of swear language words Number of positive sentiment words Number of negative sentiment words Tweet is a retweet Number of special symbols [$, !] Number of emoticons [:-), :-(] Tweet is a reply Number of @- mentions Number of retweets Time lapse since the query Has URL Number of URLs Use of URL shortener service Message based features Length of the tweet Number of words Source based features Registration age of the user Number of statuses Number of followers Number of friends Is a verified account Length of description Length of screen name Has URL Ratio of followers to followees Source based features Registration age of the user Number of statuses Number of followers
  42. 42. Evaluation Metric" 42   Evalua9on  Metric:  NDCG  (Normalized  Discounted  Cumula9ve   Gain)           NDCG  is  the  standard  metric  used  to  evaluate  “graded”  results  
  43. 43. Ranking Results" 43   •  Tweet  and  user  based  features  contribute  in  determining  the  credibility  –  it   maOers  “what  you  post  and  who  you  are”    
  44. 44. PRF" – PRF  (Pseudo  Relevance  Feedback)     - Extract  k  ranked  documents  and  then  re-­‐rank   those  documents  according  to  a  defined  score     - Re-­‐ranking  based  on  ‘top  words’  of  an  event       - Top  n  unigrams  based  on  BM25  ranking  func9on   44  
  45. 45. Algorithm" 45   SVM-­‐Rank   T1   .   .   .   .   Tn   T’1   .   .   T’k   .   T’n   Extract  top   unigrams  per   event   PRFRank  (similarity  metric)   T’’1   .   .   T’’k  
  46. 46. Ranking Results" 46   PRF  ranking  greatly  enhances  the  performance  (upto  .74  NDCG)  
  47. 47. Approach" 47   Characterizing   Misinforma$on   and  Fake  Content     Ranking   Framework  to   Assess  Credibility   Building  and   Evalua$ng  a  Real-­‐ $me  System     Detec9ng  fake  images   (Hurricane  sandy)     Analyzing  rumor   propaga9on  (Boston   blasts)     Detec9ng  user   communi9es  (three   events)     Analyzing  rumors  spread   in  India  centric  events   (Mumbai  blasts  and   Assam  riots)   14  events  data  tagging     30%  of  tweets  provide   informa9on  (17%   credible  informa9on     Linear  logis9c  regression     Present  ranking   algorithm  to  assess   credibility  in  tweets   using  pseudo  relevance   feedback   45  features  computable   for  a  single  tweet     Live  deployment:  1,800+   TwiOer  users       Credibility  score   computed  for  14+   Million  tweets     Evaluated  TweetCred  in   terms  of  response  9me,   effec9veness  and   usability   TweetCred:  Real-­‐Time  Credibility  Assessment  of  Content  on  TwiOer.  Adi9  Gupta,  Ponnurangam  Kumaraguru,  Carlos  Cas9llo   and  Patrick  Meier.  Proceedings  of  the  6th  Interna9onal  Conference  on  Social  Informa9cs  (SocInfo),  Barcelona,  Spain,  2014.   Honorable  Men$on  for  Best  Paper.  
  48. 48. TweetCred" – Available  as  a  Chrome  Extension   – Rest  API  
  49. 49. Features for Real-time Analysis" 49   Feature  set      Features  (45)     Tweet  meta-­‐data     Number  of  seconds  since  the  tweet;  Source  of  tweet  (mobile  /   web/  etc);  Tweet  contains  geo-­‐coordinates   Tweet  content  (simple)     Number  of  characters;  Number  of  words;  Number  of  URLs;   Number  of  hashtags;  Number  of  unique  characters;  Presence  of   stock  symbol;  Presence  of  happy  smiley;  Presence  of  sad  smiley;   Tweet  contains  `via';  Presence  of  colon  symbol   Tweet  content  (linguis9c)     Presence  of  swear  words;  Presence  of  nega9ve  emo9on  words;   Presence  of  posi9ve  emo9on  words;  Presence  of  pronouns;   Men9on  of  self  words  in  tweet  (I;  my;  mine)   Tweet  author     Number  of  followers;  friends;  9me  since  the  user  if  on  TwiOer;   etc.   Tweet  network     Number  of  retweets;  Number  of  men9ons;  Tweet  is  a  reply;   Tweet  is  a  retweet   Tweet  links     WOT  score  for  the  URL;  Ra9o  of  likes  /  dislikes  for  a  YouTube   video  
  50. 50. Training Data" – 500  Tweets  per  event   – Used  CrowdFlower  service   50   Event   Tweets   Users   Boston  Marathon  Blasts  (2013)   7,888,374   3,677,531   Typhoon  Haiyan  /  Yolanda  (2013)   671,918   368,269   Cyclone  Phailin  (2013)   76,136   34,776   Washington  Navy  yard  shoo9ngs   (2013)   484,609   257,682   Polar  vortex  cold  wave  (2014)   143,959   116,141   Oklahoma  Tornadoes  (2013)   809,154   542,049    Total       10,074,150   4,996,448  
  51. 51. Annotation" –  Step  1   -  R1.  Contains  informa9on  about  the  event   -  R2.  Is  related  to  the  event,  but  contains  no  informa9on   -  R3.  Not  related  to  the  event   -  R4.  Skip  tweet   45%  (class  R1),  40%  (class  R2),  and  15%  (class  R3)       –  Step  2   -  C1.  Definitely  credible   -  C2.  Seems  credible   -  C3.  Definitely  incredible   -  C4.  Skip  tweet.     52%  (class  C1),  35%  (class  C2),  and  13%  (class  C3)     51  
  52. 52. Ranking Model Evaluation" 52   AdaRank   Coord.   Ascent   RankBoost   SVM-­‐ rank   NDCG@25   0.6773   0.5358   0.6736   0.3951   NDCG@50   0.6861   0.5194   0.6825   0.4919   NDCG@75   0.6949   0.7521   0.689   0.6188   NDCG@100     0.6669   0.7607   0.6826   0.7219   Time  (training)   35-­‐40  secs   1  min   35-­‐40  secs   9-­‐10  secs   Time  (tes$ng)   <1  sec   <1  sec   <1  sec   <1  sec  
  53. 53. Top Ten Features" – No.  of  characters  in  tweet     – Unique  characters  in  tweet     – No.  of  words  in  tweet   – User  has  loca9on  in  profile     – Number  of  retweets   – Age  of  tweet   – Tweet  contains  URL   – Tweet  contains  via   – Statuses  /  Followers   – Friends  /  Followers     53  
  54. 54. Implementation"
  55. 55. Feedback by Users" 55  
  56. 56. Usage Statistics" Date  of  launch  of  TweetCred    27  Apr,  2014   Credibility  score  requests  received   14,234,131   Unique  TwiOer  users   1,808   Feedback  was  given  for  tweets   1,654   Unique  users  who  gave  feedback   364   56   *  Data  as  on  April’15  
  57. 57. Users of TweetCred" Sample  users:   - Emergency  responders   - Firefighters   - Journalists  /  news  media   - General  users   - Researchers  (Requested  API  tokens)   57  
  58. 58. System Evaluation" – Usability  Evalua9on   - System  Usability  Scale  (SUS):  70   – Response  Time   58  
  59. 59. v Media"
  60. 60. Limitations & Future Work" – Current  research  focuses  on  TwiOer,  we   would  like  analyze  credibility  of  content  on   different  social  media  using  similar   framework     – We  would  like  to  enhance  the  current   system  to  indicate  tweets  that  are  9mely,   factual,  well-­‐wriOen,  etc.   60  
  61. 61. Contributions Summary" –  Analyzed  how  real  and  fake  content  is  propagated  through  the   TwiOer  network,  with  the  purpose  of  assessing  the  reliability  of   TwiOer  as  an  informa9on  source  during  real-­‐world  events.       –  Proposed  a  learning-­‐to-­‐rank  framework  for  assessing  credibility  of   content  on  TwiOer  using  a  combina9on  of  content,  meta-­‐data,   network,  user  profile  and    temporal  features.     –  Evaluated  and  deployed  a  novel  framework  for  providing  indica9on   of  trustworthiness  /  credibility  of  tweets  posted  during  events.   61  
  62. 62. Real world Impact"   –  The  real-­‐9me  system  TweetCred  built  to  assess  credibility  of   content  on  TwiOer  is  used  by  1,808  real  TwiOer  users  to  obtain   credibility  scores  for  more  than  14.2  million  tweets.       –  A  unique  data  set  of  thousands  of  fake  images,  rumor  tweets   and  malicious  profiles  for  25+  real-­‐world  events.           62  
  63. 63. Publications" –  Peer  Reviewed  Publica9ons   -  TweetCred:  Real-­‐Time  Credibility  Assessment  of  Content  on  TwiOer.  Adi9  Gupta,  Ponnurangam   Kumaraguru,  Carlos  Cas9llo  and  Patrick  Meier.  Proceedings  of  the  6th  Interna9onal  Conference  on  Social   Informa9cs  (SocInfo),  Barcelona,  Spain,  2014.  Honorable  Men9on  for  Best  Paper.     -  $1.00  per  RT  #BostonMarathon  #PrayForBoston:  Analyzing  Fake  Content  on  TwiOer.  Adi9  Gupta,   Hemank  Lamba  and  Ponnurangam  Kumaraguru.  Accepted  at  IEEE  APWG  eCrime  Research  Summit   (eCRS),  San  Francisco,  USA,  2013.   -  Faking  Sandy:  Characterizing  and  Iden9fying  Fake  Images  on  TwiOer  during  Hurricane  Sandy.  Adi9   Gupta,  Hemank  Lamba,  Ponnurangam  Kumaraguru  and  Anupam  Joshi.  Accepted  at  the  2nd   Interna9onal  Workshop  on  Privacy  and  Security  in  Online  Social  Media  (PSOSM),  in  conjunc9on  with  the   22th  Interna9onal  World  Wide  Web  Conference  (WWW),  Rio  De  Janeiro,  Brazil,  2013.  Best  Paper  Award.   -  Iden9fying  and  Characterizing  User  Communi9es  on  TwiOer  during  Crisis  Events.  Adi9  Gupta,  Anupam   Joshi  and  Ponnurangam  Kumaraguru.  Workshop  on  Data-­‐driven  User  Behavioral  Modeling  and  Mining   from  Social  Media  (UMSOCIAL),  Co-­‐located  with  21st  ACM  Interna9onal  Conference  on  Informa9on  and   Knowledge  Management  (CIKM),  Hawaii,  USA,  2012.   -  Credibility  Ranking  of  Tweets  during  High  Impact  Events.  Adi9  Gupta  and  Ponnurangam  Kumaraguru,   Workshop  on  Privacy  and  Security  on  Online  Social  Media  (PSOSM),  co-­‐located  with  the  21st   Interna9onal  World  Wide  Web  Conference  (WWW),  Lyon,  France,  2012.   -  Beware  of  What  You  Share:  Inferring  Home  Loca9on  in  Social  Networks.  Ta9ana  Pontes,  Gabriel  Magno,   Marisa  Vasconcelos,  Adi9  Gupta,  Jussara  Almeida,  Ponnurangam  Kumaraguru  and  Virgilio  Almeida,   Privacy  in  Social  Data  (PinSoda),  in  conjunc9on  with  Interna9onal  Conference  on  Data  Mining  (ICDM)   (2012).   63  
  64. 64. Publications" –  Peer  Reviewed  Publica9ons  (Posters)   -  Analyzing  and  Measuring  Spread  of  Fake  Content  on  TwiOer  during  High   Impact  Events.  Adi9  Gupta,  Hemank  Lamba,  Ponnurangam  Kumaraguru.   Security  and  Privacy  Symposium  IIT,  Kanpur,  2014.  Best  Poster  Winner.   -  Twit-­‐Digest  Version  2:  An  Online  Solu9on  for  Analyzing  and  Visualizing   TwiOer  in  Real-­‐Time.  Adi9  Gupta,  Mayank  Gupta,  Ponnurangam   Kumaraguru.  Security  and  Privacy  Symposium  IIT,  Kanpur,  2014.   -  Twit-­‐Digest:  Real-­‐9me  TwiOer  search  portal  for  extrac9ng,  tracking  and   visualizing  informa9on.  Adi9  Gupta,  Akshit  Chhabra  and  Ponnurangam   Kumaraguru.  IBM  ICARE  2012.  2nd  Runner’s  Up  prize  Best  Poster.     -  U2P2:  Understanding  User  Privacy  Percep9ons,  Niharika  Sachdeva,   Ponnurangam  Kumaraguru  and  Adi9  Gupta,  Poster  at  IBM-­‐ICARE,  2011.   –  Book  Chapter   -  Misinforma9on  on  TwiOer  during  Crisis  Events.  Encyclopedia  of  Social   Network  Analysis  and  Mining  (ESNAM).  Adi9  Gupta,  Ponnurangam   Kumaraguru.  Book  Chapter.  Springer  publica9ons.  2012.   64  
  65. 65. Thank  you!       hOp://twitdigest.iiitd.edu.in/TweetCred/   cerc.iiitd.ac.in  

×