介手獉介手奾䯤
Ticket Management
API Monitoring Test
Manual Test
Functional
Test
Regression
Test
Exploratory
Test
%76PDQDJHDOOWLFNHWV
7HVW5DLOPDQDJHPDQXDO
WHVWFDVH
3RVWPDQPDQDJH$3,
PRQLWRULQJFDVH
How ML helps LINE Fact Checker?
• Coverage of
Verified/Unverified
Verified
Messages: 300+
Similar
Messages : 35k+
Total Messages : 40k/d
Near-
Duplication
Classification
Slide 20
Slide 20 text
Near-Duplication - Use Cases
Verified Fake Message:
• "footage on Captain's Instagram Stories showed them wearing wedding rings on their both hands, which prove
s Captain America and Captain Marvel get married in Las Vegas"
Query
Checked
Result
Type
Captain America and Captain Marvel get married in Las Vegas True Partial
The wedding in Las Vegas is hosted by Captain America and Captain Marvel
couple
True Semantically
Ironman and Black Widow get married in Los Angeles False Syntactically
Slide 21
Slide 21 text
ML models
• An Approximate Nearest Neighbor
model: find similar articles using
pretrained embeddings
• Pre-trained BERT classifier: verify
topics
• fine-tuned with TODAY articles
!"" #, %, & = ()*"+!,
#%-
./
&
+01"2ℎ4!. !"" = 5)65!"(!""8~:
)
Slide 22
Slide 22 text
ML system under hood
Predicted
Label
Training Data Ingestion
Scheduling Orchestration Async Execution
Model
Management
Model
Deployment
Index-based
Vector Search
(ANN)
Serving
Slide 23
Slide 23 text
Query Article
Near-duplicate Articles
Human evaluated results
Slide 24
Slide 24 text
Classification of Articles
Slide 25
Slide 25 text
How users are influenced?
• 46% users recognize the suspicious news
• 33% users actively do the fact check
• 25% would share the checked results
• 10x times of facts checked
• 4M+ impression of the checked fact
%
%
%