Benchmarking the Extraction and Disambiguation of Named Entities on the Semantic Web
Learning Semantic Relationships between Entities in Twitter
-
Upload
web-information-systems-tu-delft -
Category
Technology
-
view
1.826 -
download
0
description
Transcript of Learning Semantic Relationships between Entities in Twitter
![Page 1: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/1.jpg)
DelftUniversity ofTechnology
Learning Semantic Relationships between Entities in Twitter
ICWE, Cyprus, June 22, 2011
Ilknur Celik, Fabian Abel, Geert-Jan HoubenWeb Information Systems, TU Delft
![Page 2: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/2.jpg)
2Learning Semantic Relationships between Entities in Twitter
PersonalizedRecommendations
Personalized Search Adaptive Systems
What we do: Science and Engineering for the Personal Web
Social Web
Analysis and User Modeling
user/usage data
Semantic Enrichment, Linkage and Alignment
domains: news social media cultural heritage public data e-learning
![Page 3: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/3.jpg)
3Learning Semantic Relationships between Entities in Twitter
60,000,000number of tweets published per day
![Page 4: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/4.jpg)
4Learning Semantic Relationships between Entities in Twitter
1number of tweets per day that are interesting for me
![Page 5: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/5.jpg)
5Learning Semantic Relationships between Entities in Twitter
Searching on Twitter
![Page 6: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/6.jpg)
6Learning Semantic Relationships between Entities in Twitter
Issues with Multiple Keywords Search
![Page 7: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/7.jpg)
7Learning Semantic Relationships between Entities in Twitter
Let’s try to search with One Keyword
![Page 8: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/8.jpg)
8Learning Semantic Relationships between Entities in Twitter
Page 1
![Page 9: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/9.jpg)
9Learning Semantic Relationships between Entities in Twitter
Page 2
![Page 10: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/10.jpg)
10Learning Semantic Relationships between Entities in Twitter
Page 3
![Page 11: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/11.jpg)
11Learning Semantic Relationships between Entities in Twitter
Page 60!!
tweet I was looking for
Next Saturday @thatsimpsonguy aka Guilty Simpson will be performing atArea51 in my hometwon Eindhoven. #realliveshit #iwillspinrecordsabout 9 hours ago via Blackberry
Music Artist
Locations
![Page 12: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/12.jpg)
12Learning Semantic Relationships between Entities in Twitter
Is there an easier way? Faceted Search can help
Locations more...
Events more...
Music Artists:+ Guilty Simpson+ Bryan Adams+ Elton John+ Golden Earring+ Rihanna+ The eagles+ 3 Doors Downmore...
Current Query:
Results:1. Yskiddd: Next saturday
@thatsimpsonguy aka Guilty Simpson will be performing at Area51 in my homeytown Eindhoven. #realliveshit #iwillspinrecords2
2. Usee123: Cool #EV3door7980 !!! http://bit.ly/igyyRhL
3. sanmiquelmusic: This Saturday I'm joining @KrusadersMusic to Intents
Eindhoven Music
Expand Query:
![Page 13: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/13.jpg)
13Learning Semantic Relationships between Entities in Twitter
Semantic relationships between entities are essential to realize such applications.
Music Artist:Guilty Simpson
Location:Eindhoven
Location:Area51
![Page 14: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/14.jpg)
14Learning Semantic Relationships between Entities in Twitter
Relation Discovery Framework
news articles
microblog posts Entity
extraction &semantic
enrichment
Person A Location A
Location B
Event A
Group A
temporal constraints
relation type
weighting scheme
sourceselection
Relation discovery
Person A Location A
Group A
isLocatedIn
Person AinvolvedIn
typed relations
Applications- Browsing support- Query suggestions- Schema enrichment
Relation Discovery Framework
![Page 15: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/15.jpg)
15Learning Semantic Relationships between Entities in Twitter
Entity Extraction and Semantic Enrichment
@bob: Julian Assange got arrested http://bit.ly/5d4r2t
Julian Assange
Julian Assange Tweet-basedenrichment
Julian Assange arrestedJulian Assange, the founder ofWikiLeaks, is under arrest inLondon…
News-basedenrichment
Julian Assange
London
WikiLeaks
Julian Assange Julian Assange
LondonWikiLeaks
powered by
![Page 16: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/16.jpg)
16Learning Semantic Relationships between Entities in Twitter
Relation Learning Strategies
• Relation: relation(e1, e2, type, tstart, tend, weight)
• Relation Learning strategy: • Input: entity e1 and e2, time period (tstart, tend)• Challenge: infer weight and type of the relation for the given
• Weighting according to co-occurrence frequency:a) Tweet-based: count co-occurrence in tweetsb) News-based: count co-occurrence in newsc) Tweet-News-based: count co-occurrence in both tweets and
news
entities
type/label of relation
time period
relatedness
![Page 17: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/17.jpg)
17Learning Semantic Relationships between Entities in Twitter
Research Questions1. Which strategy performs best in detecting
relationships between entities?
2. Does the accuracy depend on the type of entities which are involved in a relation?
3. How do the strategies perform for discovering relationships which have temporal constraints (trending relationships)?
![Page 18: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/18.jpg)
18Learning Semantic Relationships between Entities in Twitter
Dataset
timeNov 15 Dec 15 Jan 15
20,000 Twitter users
10,000,000 tweets
2 months
more than:
75,000 news
WikiLeaks founder, Julian Assange, under arrest in
London
![Page 19: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/19.jpg)
19Learning Semantic Relationships between Entities in Twitter
Dataset Characteristics
![Page 20: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/20.jpg)
20Learning Semantic Relationships between Entities in Twitter
Tweets and news articles per day50,000-400,000tweets per day
100-1000 news articles
per day
![Page 21: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/21.jpg)
21Learning Semantic Relationships between Entities in Twitter
Entities referenced per day 10,000-100,000entity ref. in tweetsper day
5,000-20,000 entity ref.in newsper day
~40% tweets do not mention any
(recognizable) entity
99.3% of the news articles mention at
least one (recognizable) entity
72.6% of the top 1000 mentioned entities in Twitter are also mentioned in the mainstream
news media
![Page 22: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/22.jpg)
22Learning Semantic Relationships between Entities in Twitter
Number of Distinct Entities per Entity Types
39 types of entities
![Page 23: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/23.jpg)
23Learning Semantic Relationships between Entities in Twitter
Performance of Relation Learning Strategies
![Page 24: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/24.jpg)
24Learning Semantic Relationships between Entities in Twitter
Our Ground Truth of true relations
1. Based on DBpedia:• We mapped entities to their corresponding DBpedia
resources• No appropriate DBpedia URIs for more than 35% of the entities
• We analyzed whether there is a direct relation between two entities
2. Based on user study:• Participants judged whether two entities are really:
a) related (62.6% were rated as related)
b) related in the given time period (57.3% were rated as related)• Overall: 2588 judgments
Thank you!
![Page 25: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/25.jpg)
25Learning Semantic Relationships between Entities in Twitter
1. Which strategy performs best in detecting relationships between entities?
![Page 26: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/26.jpg)
26Learning Semantic Relationships between Entities in Twitter
Accuracy of relation discovery
Based on user study Based on DBpediaCombining both tweet-based and news-based
strategies allows for highest accuracy
![Page 27: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/27.jpg)
27Learning Semantic Relationships between Entities in Twitter
F-Measure@k
Tweet-based strategy
saturates quickly
Combined strategy (and news-based) increase in
performance.
![Page 28: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/28.jpg)
28Learning Semantic Relationships between Entities in Twitter
2. Does the accuracy depend on the type of entities which are involved in a relation?
![Page 29: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/29.jpg)
29Learning Semantic Relationships between Entities in Twitter
Does the accuracy depend on the type of entities?
Relationships which involve events can be discovered with
high precision
92%
87% precision
23%
26% precision
![Page 30: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/30.jpg)
30Learning Semantic Relationships between Entities in Twitter
Does the accuracy depend on the type of entities? (cont.)
Relationships between persons/groups are difficult to
detect.
Relationships between events can
be detected with highest precision.
![Page 31: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/31.jpg)
31Learning Semantic Relationships between Entities in Twitter
3. How do the strategies perform for discovering relationships which have temporal constraints?
![Page 32: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/32.jpg)
32Learning Semantic Relationships between Entities in Twitter
Relationships with temporal constraints
Tweet-based strategy performs better in discovering relationships that are valid only for a specific period
in time
![Page 33: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/33.jpg)
33Learning Semantic Relationships between Entities in Twitter
Where do relationships emerge faster?
time difference (in days) of first occurrence of relationship
News is faster Twitter is faster
Speed of strategies is domain-dependent
![Page 34: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/34.jpg)
34Learning Semantic Relationships between Entities in Twitter
Conclusions and Future Work
What we did: relation discovery framework based on Twitter
Findings:1. Strategy that considers both tweets and (linked) news
articles allows for highest accuracy2. Performance varies for different domains (e.g. event-
relationships can be detected with highest precision)3. Tweet-based strategy allows for detecting
relationships, which have a restricted temporal validity, with high precision (and fast)
Ongoing work: Adaptive Faceted Search on Twitterhttp://wis.ewi.tudelft.nl/tweetum/
![Page 35: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/35.jpg)
35Learning Semantic Relationships between Entities in Twitter
Relation Discovery for Adaptive Faceted Search
Locations more...
Events more...
Music Artists:+ Guilty Simpson+ Bryan Adams+ Elton John+ Golden Earring+ Rihanna+ The eagles+ 3 Doors Downmore...
Current Query:
Results:1. Yskiddd: Next saturday
@thatsimpsonguy aka Guilty Simpson will be performing at Area51 in my homeytown Eindhoven. #realliveshit #iwillspinrecords2
2. Usee123: Cool #EV3door7980 !!! http://bit.ly/igyyRhL
3. sanmiquelmusic: This Saturday I'm joining @KrusadersMusic to Intents
Eindhoven Music
Expand Query:
1. Analyze (temporal) relationships of entities of the
“current query” to adapt facet ranking.
2. Analyze (temporal)relationships of entities that appear in the user profile to adapt facet
ranking.
user
![Page 36: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/36.jpg)
36Learning Semantic Relationships between Entities in Twitter
Thank you!
Ilknur Celik, Fabian Abel, Geert-Jan Houben
Twitter: @perswebhttp://wis.ewi.tudelft.nl/tweetum/
![Page 37: Learning Semantic Relationships between Entities in Twitter](https://reader034.fdocuments.in/reader034/viewer/2022052619/55504e00b4c90580748b52fe/html5/thumbnails/37.jpg)
37Learning Semantic Relationships between Entities in Twitter
The Social Web
Help me to tackle the
information overload!
Recommend me news articles
that now interest me!
Help me to find interesting (social) media!
Do not bother me with
advertisements that are not
interesting for me!
Give me personalized
support when I do my online training!
Who is this? What are his personal demands? How can we make him happy?
Personalize my Web
experience!