vandalism detection in wikidata - imt · vandalism detection in wikidata stefan heindorf1, martin...
TRANSCRIPT
Vandalism Detection in WikidataStefan Heindorf1, Martin Potthast2, Benno Stein2, Gregor Engels1
CIKM 2016October 25, 2016
1 2
3Stefan HeindorfVandalism Detection in Wikidata
(Feb 22, 2013)
(May 13, 2013)
(May 30, 2013)
Item head
Item body
Revisions
3Stefan HeindorfVandalism Detection in Wikidata
(Feb 22, 2013)
(May 13, 2013)
(May 30, 2013)
Item head
Item body
Revisions
3Stefan HeindorfVandalism Detection in Wikidata
(Feb 22, 2013)
(May 13, 2013)
(May 30, 2013)
Item head
Item body
Revisions
Why is it a problem?
4
Patrolling Reverting Warning Blocking Protecting
• Over 2 Mio manual edits per month• A lot of tedious work• Vandalism is not detected in time
Stefan HeindorfVandalism Detection in Wikidata
Research Question
How to detect damaging changes tocrowdsourced knowledge bases?
5Stefan HeindorfVandalism Detection in Wikidata
Our Approach
1. Label Dataset Vandalism Corpus [SIGIR’15]
Vandalism Detection in Wikidata Stefan Heindorf 6
Our Approach
1. Label Dataset Vandalism Corpus [SIGIR’15]2. Study Vandalism Characteristics 47 Features
Vandalism Detection in Wikidata Stefan Heindorf 6
Our Approach
1. Label Dataset Vandalism Corpus [SIGIR’15]2. Study Vandalism Characteristics 47 Features3. Experiment with ML Multiple-Instance Learning
Vandalism Detection in Wikidata Stefan Heindorf 6
Our Approach
1. Label Dataset Vandalism Corpus [SIGIR’15]2. Study Vandalism Characteristics 47 Features3. Experiment with ML Multiple-Instance Learning4. Compare with state of the art 2 Baselines
Vandalism Detection in Wikidata Stefan Heindorf 6
Corpus [SIGIR ’15]
Revisions over time
7Month
103,000 vandalism revisions24 million manual revisions
Corpus [SIGIR ’15]
Revisions over time
7Month
103,000 vandalism revisions24 million manual revisions
0.4% vandalism
Corpus [SIGIR ’15]
Revisions over time
7
Item head(1.3% vandalism)
Month
103,000 vandalism revisions24 million manual revisions
0.4% vandalism
Corpus [SIGIR ’15]
Revisions over time
7
Item head(1.3% vandalism)
Item body(0.2% vandalism)
Month
103,000 vandalism revisions24 million manual revisions
0.4% vandalism
Corpus [SIGIR ’15]
Revisions over time
7
Item head(1.3% vandalism)
Item body(0.2% vandalism)Training
Month
103,000 vandalism revisions24 million manual revisions
0.4% vandalism
Corpus [SIGIR ’15]
Revisions over time
7
Item head(1.3% vandalism)
Item body(0.2% vandalism)Training
Validation
Month
103,000 vandalism revisions24 million manual revisions
0.4% vandalism
Corpus [SIGIR ’15]
Revisions over time
7
Item head(1.3% vandalism)
Item body(0.2% vandalism)Training
TestValidation
Month
103,000 vandalism revisions24 million manual revisions
0.4% vandalism
Content Features11 Character features (e.g., lowerCaseRatio, digitRatio) 9 Word features (e.g., badWordRatio)4 Sentence features (e.g., commentSitelinkSimilarity)3 Statement features (e.g., propertyFrequency)
Context Features10 User features (e.g., userCountry)2 Item features (e.g., logItemFrequency)8 Revision features (e.g., revisionTag, revisionLanguage)
Features (47 in total)
Stefan Heindorf 8Vandalism Detection in Wikidata
Features (47 in total)
Stefan Heindorf 8Vandalism Detection in Wikidata
revisionTag Vand. Total Prob.Rev. with tags 52 T 8,619 T 0.60%
By abuse filter 49 T 122 T 39.90%By editing tools 3 T 8,496 T 0.03%
Rev. w/o tags 52 T 15,386 T 0.34%
revisionTag
Features (47 in total)
Stefan Heindorf 8Vandalism Detection in Wikidata
revisionTag Vand. Total Prob.Rev. with tags 52 T 8,619 T 0.60%
By abuse filter 49 T 122 T 39.90%By editing tools 3 T 8,496 T 0.03%
Rev. w/o tags 52 T 15,386 T 0.34%
revisionTag
Features (47 in total)
Stefan Heindorf 8Vandalism Detection in Wikidata
revisionTag Vand. Total Prob.Rev. with tags 52 T 8,619 T 0.60%
By abuse filter 49 T 122 T 39.90%By editing tools 3 T 8,496 T 0.03%
Rev. w/o tags 52 T 15,386 T 0.34%
revisionTag
Features (47 in total)
Stefan Heindorf 8Vandalism Detection in Wikidata
revisionTag Vand. Total Prob.Rev. with tags 52 T 8,619 T 0.60%
By abuse filter 49 T 122 T 39.90%By editing tools 3 T 8,496 T 0.03%
Rev. w/o tags 52 T 15,386 T 0.34%
revisionTag
Multiple-Instance Learning
• Observation: Vandalism seldom occurs in isolation
Vandalism Detection in Wikidata Stefan Heindorf 9
Multiple-Instance Learning
• Observation: Vandalism seldom occurs in isolation
Vandalism Detection in Wikidata Stefan Heindorf 9
22:35, 11 September 2013 184.19.64.111 (talk) . . (Changed English label: Barack Obama Aloha)
22:35, 11 September 2013 184.19.64.111 (talk) . . (Added English alias: Lulu:):):):):):):))
12:05, 11 September 2013 MatmaBot (talk | contribs) . . (Changed Polish description: imported
Multiple-Instance Learning
• Observation: Vandalism seldom occurs in isolation
Vandalism Detection in Wikidata Stefan Heindorf 9
22:35, 11 September 2013 184.19.64.111 (talk) . . (Changed English label: Barack Obama Aloha)
22:35, 11 September 2013 184.19.64.111 (talk) . . (Added English alias: Lulu:):):):):):):))
12:05, 11 September 2013 MatmaBot (talk | contribs) . . (Changed Polish description: imported
Multiple-Instance Learning
• Observation: Vandalism seldom occurs in isolation
Vandalism Detection in Wikidata Stefan Heindorf 9
22:35, 11 September 2013 184.19.64.111 (talk) . . (Changed English label: Barack Obama Aloha)
22:35, 11 September 2013 184.19.64.111 (talk) . . (Added English alias: Lulu:):):):):):):))
12:05, 11 September 2013 MatmaBot (talk | contribs) . . (Changed Polish description: imported
Session 1
Session 2
Multiple-Instance Learning
• Observation: Vandalism seldom occurs in isolation
• Idea: Apply Multiple-Instance Learning
Vandalism Detection in Wikidata Stefan Heindorf 9
22:35, 11 September 2013 184.19.64.111 (talk) . . (Changed English label: Barack Obama Aloha)
22:35, 11 September 2013 184.19.64.111 (talk) . . (Added English alias: Lulu:):):):):):):))
12:05, 11 September 2013 MatmaBot (talk | contribs) . . (Changed Polish description: imported
Session 1
Session 2
Multiple-Instance Learning
• Observation: Vandalism seldom occurs in isolation
• Idea: Apply Multiple-Instance Learning
Vandalism Detection in Wikidata Stefan Heindorf 9
22:35, 11 September 2013 184.19.64.111 (talk) . . (Changed English label: Barack Obama Aloha)
22:35, 11 September 2013 184.19.64.111 (talk) . . (Added English alias: Lulu:):):):):):):))
12:05, 11 September 2013 MatmaBot (talk | contribs) . . (Changed Polish description: imported
Session 1
Session 2
Multiple-Instance Learning
• Observation: Vandalism seldom occurs in isolation
• Idea: Apply Multiple-Instance Learning
Vandalism Detection in Wikidata Stefan Heindorf 9
22:35, 11 September 2013 184.19.64.111 (talk) . . (Changed English label: Barack Obama Aloha)
22:35, 11 September 2013 184.19.64.111 (talk) . . (Added English alias: Lulu:):):):):):):))
12:05, 11 September 2013 MatmaBot (talk | contribs) . . (Changed Polish description: imported
Session 1
Session 2
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
10Vandalism Detection in Wikidata Stefan Heindorf
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
10Vandalism Detection in Wikidata Stefan Heindorf
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10Vandalism Detection in Wikidata Stefan Heindorf
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10
0
0.2
0.4
0.6
0.8
1
0 0.2 0.4 0.6 0.8 1
Prec
ision
RecallVandalism Detection in Wikidata Stefan Heindorf
Test Dataset (0.2% vandalism)
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10
0
0.2
0.4
0.6
0.8
1
0 0.2 0.4 0.6 0.8 1
Prec
ision
RecallVandalism Detection in Wikidata Stefan Heindorf
FILTER
Test Dataset (0.2% vandalism)
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10
0
0.2
0.4
0.6
0.8
1
0 0.2 0.4 0.6 0.8 1
Prec
ision
RecallVandalism Detection in Wikidata Stefan Heindorf
ORES
FILTER
Test Dataset (0.2% vandalism)
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10
0
0.2
0.4
0.6
0.8
1
0 0.2 0.4 0.6 0.8 1
Prec
ision
RecallVandalism Detection in Wikidata Stefan Heindorf
ORES
FILTER
Test Dataset (0.2% vandalism)
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10
0
0.2
0.4
0.6
0.8
1
0 0.2 0.4 0.6 0.8 1
Prec
ision
RecallVandalism Detection in Wikidata Stefan Heindorf
ORES
FILTER
Test Dataset (0.2% vandalism)
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10
0
0.2
0.4
0.6
0.8
1
0 0.2 0.4 0.6 0.8 1
Prec
ision
RecallVandalism Detection in Wikidata Stefan Heindorf
ORES
FILTER
PR-AUC: 0.491ROC-AUC: 0.991
Test Dataset (0.2% vandalism)
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10
0
0.2
0.4
0.6
0.8
1
0 0.2 0.4 0.6 0.8 1
Prec
ision
RecallVandalism Detection in Wikidata Stefan Heindorf
Detect and revert 30% vandalismfully automatically
ORES
FILTER
Test Dataset (0.2% vandalism)
WDVD vs. Baselines
• WDVD (our approach)Wikidata Vandalism Detector
• FILTER (baseline)Wikidata Abuse Filter
• ORES (baseline)Objective Revision Evaluation Service
10
0
0.2
0.4
0.6
0.8
1
0 0.2 0.4 0.6 0.8 1
Prec
ision
RecallVandalism Detection in Wikidata Stefan Heindorf
Detect and revert 30% vandalismfully automatically
ORES
FILTER
• Reduce workload by factor 10(precision 2% instead of 0.2%)
Still find 98.8% of all vandalism
Test Dataset (0.2% vandalism)
Conclusion and Outlook
Conclusion• Vandalism: Concentration on item heads (currently)• Features: Content & Context• Model: Multiple-Instance• PR-AUC: 0.491• ROC-AUC: 0.991
Stefan Heindorf 11Vandalism Detection in Wikidata
Conclusion and Outlook
Conclusion• Vandalism: Concentration on item heads (currently)• Features: Content & Context• Model: Multiple-Instance• PR-AUC: 0.491• ROC-AUC: 0.991
Stefan Heindorf 11Vandalism Detection in Wikidata
Code + Data: http://www.heindorf.me/wdvd.html
Conclusion and Outlook
Conclusion• Vandalism: Concentration on item heads (currently)• Features: Content & Context• Model: Multiple-Instance• PR-AUC: 0.491• ROC-AUC: 0.991
Outlook• Goal: Better detection (on item bodies)• Idea: Double-check with other sources
Stefan Heindorf 11Vandalism Detection in Wikidata
Code + Data: http://www.heindorf.me/wdvd.html
Conclusion and Outlook
Conclusion• Vandalism: Concentration on item heads (currently)• Features: Content & Context• Model: Multiple-Instance• PR-AUC: 0.491• ROC-AUC: 0.991
Outlook• Goal: Better detection (on item bodies)• Idea: Double-check with other sources
Stefan Heindorf 11Vandalism Detection in Wikidata
Code + Data: http://www.heindorf.me/wdvd.html
Join the competition:Vandalism Detection @WSDM Cup 2017http://www.wsdm-cup-2017.org/
Conclusion and Outlook
Conclusion• Vandalism: Concentration on item heads (currently)• Features: Content & Context• Model: Multiple-Instance• PR-AUC: 0.491• ROC-AUC: 0.991
Outlook• Goal: Better detection (on item bodies)• Idea: Double-check with other sources
Acknowledgement• German Research Foundation (DFG)• SIGIR Student Travel Grant
Stefan Heindorf 11Vandalism Detection in Wikidata
Code + Data: http://www.heindorf.me/wdvd.html
Join the competition:Vandalism Detection @WSDM Cup 2017http://www.wsdm-cup-2017.org/
Conclusion and Outlook
Conclusion• Vandalism: Concentration on item heads (currently)• Features: Content & Context• Model: Multiple-Instance• PR-AUC: 0.491• ROC-AUC: 0.991
Outlook• Goal: Better detection (on item bodies)• Idea: Double-check with other sources
Acknowledgement• German Research Foundation (DFG)• SIGIR Student Travel Grant
Stefan Heindorf 11Vandalism Detection in Wikidata
Code + Data: http://www.heindorf.me/wdvd.html
Join the competition:Vandalism Detection @WSDM Cup 2017http://www.wsdm-cup-2017.org/
Thank you!