SlideShare ist ein Scribd-Unternehmen logo
1 von 22
Downloaden Sie, um offline zu lesen
Ismaïl BADACHE, Mohand BOUGHANEM
IRIT, Toulouse University, France
{badache, boughanem}@irit.fr
Warsaw, Poland
Presentation Plan
Introduction
Related Work
Approach of Social Information Retrieval
Experimental Results4
1
3
Conclusion
2
5
1.1 Emergence of social Web
1
Number of active users 2013
1,2 1,4
1,7
2,4
2011 2012 2013 2014
Number of Internet users
Social content per 1 minute
41000 Publications
1,8 Million Like
~350 GB of Data
Facebook
Source:
blogdumoderateur.com
quantcast.com
semiocast.com
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
Video
Photo
Web Page
Web Resources
Resource
.
.
.
Social Networks
Bookmark
Comment
Share/Recommend
Motion/Vote
Like/+1
Interaction
Extraction and quantification of
social properties
Information Retrieval Model
(Ranking)
Integration
Query
2
Results
Fig 1. Global presentation of our work
Social Signals
(Source of Evidence)
Popularity
Reputation
Freshness
3
1.2 Example of Social Signals
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
1.3 Research Issues
Can these social data help the search systems for guiding the users to reach a
better quality or more relevant content?
2
How effective is each individual social signal for ranking resources for a
given query? What are the ranking correlations created by these social data?
3
4
How to combine these social data in form of social properties? What are the
most useful of them to take into account in a model search?
4
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
1
What happens when a user clicks on like or dislike button or posts a
comment for a resource, say a Web page, photo or video?
Sources of evidence (Social Features) Properties Models Authors
• Number of : clicks, votes, records and
recommendations.
Popularity
Importance
Linear
combination
(Karweg et al., 2011)
• Number of : like, dislike, comments on
YouTube.
• The playcount (number of times a user
listens to a track on lastfm)
Importance
Machine
learning
and
Linear
combination
(Chelaru et al., 2012)
(Khodaei et al. 2012)
• Presence of a URL in a tweet. (Alonso et al., 2010)
• Number of retweets.
• Number of annotations (tags).
Popularity
Machine
learning
(Yang et al., 2012)
(Hong et al., 2011)
(Pantel et al., 2012)
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
2.1 Related Work
5
• Our IR approach consists of exploiting various and heterogeneous social
signals from different social networks to define social properties to take into
account in retrieval model. We associate to each Web resource a priori relevance
based on these social properties. This relevance is then combined with a classical
topical relevance.
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
3.1 A Modular Approach for Social IR
6
• We assume that resource r can be represented both by a set of textual key-words
𝑟𝑤={𝑤1, 𝑤2, … 𝑤 𝑛} and a set of social actions (signals) performed on this
resource, 𝑟𝑎={𝑎1, 𝑎2, … 𝑎 𝑚}.
• We consider a set X={Popularity, Reputation, Freshness} of 3 social properties
that characterize a resource r. Each property is quantified by a specific actions
group. These properties are considered as a priori knowledge of a resource.
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
3.2 Social Signals and Social Properties
7
Web Resource
- Textual key-words
- Social Signals
- Like
- +1
- Share
- Comment
- Dates of actions
Web Resource
- Textual key-words
- Social Signals
- Like
- +1
- Share
- Comment
- Dates of actions
Reputation
Popularity
Freshness
𝑓𝑥 𝑟, 𝐺 =
𝑖=1, 𝑎 𝑖
𝑥
∈ 𝐴
𝑚
𝐶𝑜𝑢𝑛𝑡 (𝑎𝑖
𝑥
, 𝑟, 𝐺)
3.1 Proposed Approach
• Popularity: The resource popularity can be estimated according to the rate of
sharing this resource on social networks.
• Reputation: The resource reputation can be estimated based on social activities
that have positive meaning such as Facebook like. Indeed, resource reputation
depends on the degree of users' appreciation on social networks.
The general formula is the following:
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
3.3 Estimation of Popularity and Reputation
8
𝑓𝑥(𝑟, 𝐺) 𝑁𝑜𝑟𝑚=
𝑓𝑥 𝑟, 𝐺 − 𝑀𝐼𝑁(𝑓𝑥 𝑟, 𝐺 )
𝑀𝐴𝑋 𝑓𝑥 𝑟, 𝐺 − 𝑀𝐼𝑁(𝑓𝑥 𝑟, 𝐺 )
(1)
(2)
3.1 Proposed Approach
• Let 𝑇𝑎 𝑖
={𝑡1,𝑎 𝑖
, 𝑡2,𝑎 𝑖
, … 𝑡 𝑘,𝑎 𝑖
} a set of k moments (date) at which action 𝑎𝑖 was
produced. A moment t represents the datetime for each action a of the same type.
• Freshness: We assume that a resource is fresh if recent social signals were
associated with it. For that purpose, we define freshness as follows:
"a date of each social action (e.g., date of comment, date of share) performed on a
resource on social networks can be exploited to measure the recency of these social
actions, hence the freshness of information".
Its formula is the following:
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
3.4 Estimation of Freshness
9
𝑓𝐹 𝑟, 𝐺 =
1
1
𝑚 𝑖=1
𝑚
(
1
𝑘 𝑗=1
𝑘
𝑇𝑖𝑚𝑒(𝑡𝑗,𝑎 𝑖
, 𝑟, 𝐺))
(3)
3.1 Proposed Approach
• The combination of topical relevance with social relevance is given by the
following formula:
• Social Score: Regarding the social score 𝑅𝑒𝑙 𝑆(𝑞, 𝑟, 𝐺), we specify that this
score takes into account these social properties, which are in the form of three
normalized factors that are combined linearly by the following formula:
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
Score of Topical
Relevance
Score of Social
Relevance
𝑅𝑒𝑙 𝑞, 𝑟, 𝐺 = α ∙ 𝑅𝑒𝑙 𝑇(𝑞, 𝑟) + (1 - α) ∙ 𝑅𝑒𝑙 𝑆(𝑞, 𝑟, 𝐺)
Freshness
𝑅𝑒𝑙 𝑆 𝑞, 𝑟, 𝐺 = β ∙ 𝑓𝐹(𝑟, 𝐺) + λ ∙ 𝑓𝑃(𝑟, 𝐺) + δ ∙ 𝑓𝑅(𝑟, 𝐺)
Popularity Reputation
3.5 First Method : Linear Combination
10
(4)
(5)
3.1 Proposed Approach
1. Introduction 2. Related Work
5. Conclusion
3. Approach of SIR
4. Experimental Results
3.6 Second Method : Machine Learning Models
11
Original
Dataset
Training Dataset
Attribute Selection
Algorithms
- WrapperSubsetEval1
- CfsSubsetEval1
- ReliefFAttributeEval2
- SVMAttributeEval3
Learning Algorithms
- Naïve Bayes1
- J482
- SVM3
Cross-Fold
Evaluation
Repeat 5 x for 5-Fold Cross Validation
Fig 2. Machine Learning Process
Topical model results
for all topics
3.1 Proposed Approach
• Objectives
1. Studying the impact of each individual integration of social signals on the
performance of retrieval process.
2. Studying the impact of combining these social signals as social properties.
3. Studying the ranking correlation between social signals and relevance.
• Evaluation challenge
1. Absence of a standard framework for evaluation in social IR.
2. Collect social signals from 5 social networks and mount experimentation.
1. Introduction 2. Related Work
5. Conclusion
4.1 Experimental Evaluation
12
3. Approach of SIR
4. Experimental Results
3.1 Proposed Approach
• Textual Content: 32706 Documents Film in English extracted from IMDb.
• Social Content: 8 social data from 5 social networks.
1. Introduction 2. Related Work
5. Conclusion
4.2 Description of DataSet
13
3. Approach of SIR
4. Experimental Results
ID Title Year Released Runtime Genre Director Writer Actors Plot Poster url
- indexed indexed indexed indexed indexed indexed indexed indexed indexed - -
ACEBOOK
Like
Share
Comment
Date of last action
WITTER
Tweet
GOOGLE+
+1
Share
LINKEDDELICIOUS
Bookmark
3.1 Proposed Approach
1. Introduction 2. Related Work
5. Conclusion
4.3 Quantifying of Social Properties
14
3. Approach of SIR
4. Experimental Results
Social Properties Social Signals Social Networks
Popularity P
Number of « Comment » C1 Facebook
Number of « Tweet » C2 Twitter
Number of « Share » C3 LinkedIn
Number of « Share » C4 Facebook
Reputation R
Number of « Like » C5 Google+
Number of « +1 » C6 Facebook
Number of « Bookmark » C7 Delicious
Freshness F Date of last action C8 Facebook
• Each social property is quantified based on social signals according to their
nature and signification.
3.1 Proposed Approach
1. Introduction 2. Related Work
5. Conclusion
4.4 Results: Linear Combination
15
3. Approach of SIR
4. Experimental Results
0
0,1
0,2
0,3
0,4
0,5
0,6
Like Share Comment Tweet Mention+1 Share(LIn) Bookmark
Individual Integration of Social Signals
0
0,1
0,2
0,3
0,4
0,5
0,6
0,7
Freshness F Reputation R Popularity P R+F P+F P+R All Properties
Different Combinations of Social Signals (Social Properties)
0
0,1
0,2
0,3
0,4
BM25 Lucene Model
Baselines (Topical Models)
P@10 P@20 nDCG@10 nDCG@20
Facebook signals
3.1 Proposed Approach
1. Introduction 2. Related Work
5. Conclusion
4.5 Results: Machine Learning
16
3. Approach of SIR
4. Experimental Results
Table 1. Selected Social Signals With Attribute Selection Algorithms
++ : Highly selected
+ : Moderately selected
3.1 Proposed Approach
1. Introduction 2. Related Work
5. Conclusion
4.5 Results: Machine Learning
17
3. Approach of SIR
4. Experimental Results
Naïve Bayes SVM J48
P@20 0,5105 0,5131 0,689
0,5105 0,5131
0,689
0
0,1
0,2
0,3
0,4
0,5
0,6
0,7
0,8
Naïve Bayes
(CFS)
Naïve Bayes
(WRP)
SVM
(SVM)
J48 (RLF)
P@20 0,5315 0,5105 0,5131 0,689
0,5315 0,5105 0,5131
0,689
0
0,1
0,2
0,3
0,4
0,5
0,6
0,7
0,8
Machine learning results with using Attribute
Selection Algorithms
Machine learning without using Attribute
Selection Algorithms
3.1 Proposed Approach
1. Introduction 2. Related Work
5. Conclusion
4.6 Results: Ranking Correlation Analysis
18
3. Approach of SIR
4. Experimental Results
Fig 3. Spearman correlation between social signals and relevance
Fig 4. Spearman correlation between social properties and relevance
3.1 Proposed Approach
1. Introduction 2. Related Work
5. Conclusion
5. Conclusion
19
3. Proposed Approaches
4. Experimental Results
• Social Information Retrieval Model
- Topical relevance (retrieval model based content only).
- Social relevance (retrieval model based content and social features).
- Attribute selection algorithms and machine learning.
• Experimental Evaluation
- Superiority of proposed approach compared to textual models (baselines).
- Positive ranking correlation between social signals and relevance.
• Perspectives
- Integration of other social features.
- Further study on the impact of the temporal property.
- Comparison of the proposed models with other social models.
- Experimental evaluation on larger dataset.
http://www.irit.fr/~Ismail.Badache/

Weitere ähnliche Inhalte

Was ist angesagt?

Recommender system algorithm and architecture
Recommender system algorithm and architectureRecommender system algorithm and architecture
Recommender system algorithm and architecture
Liang Xiang
 

Was ist angesagt? (14)

Community-based Crowdsourcing
Community-based CrowdsourcingCommunity-based Crowdsourcing
Community-based Crowdsourcing
 
Tutorial on Relationship Mining In Online Social Networks
Tutorial on Relationship Mining In Online Social NetworksTutorial on Relationship Mining In Online Social Networks
Tutorial on Relationship Mining In Online Social Networks
 
Graph Neural Networks for Recommendations
Graph Neural Networks for RecommendationsGraph Neural Networks for Recommendations
Graph Neural Networks for Recommendations
 
Fundamentals of Deep Recommender Systems
 Fundamentals of Deep Recommender Systems Fundamentals of Deep Recommender Systems
Fundamentals of Deep Recommender Systems
 
Introduction to Recommender System
Introduction to Recommender SystemIntroduction to Recommender System
Introduction to Recommender System
 
Twitter Analytics
Twitter AnalyticsTwitter Analytics
Twitter Analytics
 
Pydata Taipei 2020
Pydata Taipei 2020Pydata Taipei 2020
Pydata Taipei 2020
 
Communication between open source developers
Communication between open source developersCommunication between open source developers
Communication between open source developers
 
Recommender system algorithm and architecture
Recommender system algorithm and architectureRecommender system algorithm and architecture
Recommender system algorithm and architecture
 
On the Origins of Memes by Means of Fringe Web Communities - Invited talk ta ...
On the Origins of Memes by Means of Fringe Web Communities - Invited talk ta ...On the Origins of Memes by Means of Fringe Web Communities - Invited talk ta ...
On the Origins of Memes by Means of Fringe Web Communities - Invited talk ta ...
 
CSE509 Lecture 5
CSE509 Lecture 5CSE509 Lecture 5
CSE509 Lecture 5
 
Learning to Classify Users in Online Interaction Networks
Learning to Classify Users in Online Interaction NetworksLearning to Classify Users in Online Interaction Networks
Learning to Classify Users in Online Interaction Networks
 
Collaborative filtering for recommendation systems in Python, Nicolas Hug
Collaborative filtering for recommendation systems in Python, Nicolas HugCollaborative filtering for recommendation systems in Python, Nicolas Hug
Collaborative filtering for recommendation systems in Python, Nicolas Hug
 
Live Social Semantics @ ESWC2010
Live Social Semantics @ ESWC2010Live Social Semantics @ ESWC2010
Live Social Semantics @ ESWC2010
 

Ähnlich wie Harnessing social signals to enhance a search

Ieml social recommendersystems
Ieml social recommendersystemsIeml social recommendersystems
Ieml social recommendersystems
Antonio Medina
 

Ähnlich wie Harnessing social signals to enhance a search (20)

SocialCom09-tutorial.pdf
SocialCom09-tutorial.pdfSocialCom09-tutorial.pdf
SocialCom09-tutorial.pdf
 
Practical Applications for Social Network Analysis in Public Sector Marketing...
Practical Applications for Social Network Analysis in Public Sector Marketing...Practical Applications for Social Network Analysis in Public Sector Marketing...
Practical Applications for Social Network Analysis in Public Sector Marketing...
 
Pebble-in-the-Pond?!
Pebble-in-the-Pond?!Pebble-in-the-Pond?!
Pebble-in-the-Pond?!
 
Social Event Detection using Multimodal Clustering and Integrating Supervisor...
Social Event Detection using Multimodal Clustering and Integrating Supervisor...Social Event Detection using Multimodal Clustering and Integrating Supervisor...
Social Event Detection using Multimodal Clustering and Integrating Supervisor...
 
SRS presentation
SRS presentationSRS presentation
SRS presentation
 
Collaboration between Software Developers and the Impact of Proximity
Collaboration between Software Developers  and the Impact of ProximityCollaboration between Software Developers  and the Impact of Proximity
Collaboration between Software Developers and the Impact of Proximity
 
Tools and Tips for Analyzing Social Media Data
Tools and Tips for Analyzing Social Media DataTools and Tips for Analyzing Social Media Data
Tools and Tips for Analyzing Social Media Data
 
Online Multi-user Interactive Learning Activities on Social Cloud
Online Multi-user Interactive Learning Activities on Social CloudOnline Multi-user Interactive Learning Activities on Social Cloud
Online Multi-user Interactive Learning Activities on Social Cloud
 
Seams2016 presentation calikli_et_al
Seams2016 presentation calikli_et_alSeams2016 presentation calikli_et_al
Seams2016 presentation calikli_et_al
 
Ieml social recommendersystems
Ieml social recommendersystemsIeml social recommendersystems
Ieml social recommendersystems
 
22 An Introduction to Stochastic Actor-Oriented Models (SAOM or Siena)
22 An Introduction to Stochastic Actor-Oriented Models (SAOM or Siena)22 An Introduction to Stochastic Actor-Oriented Models (SAOM or Siena)
22 An Introduction to Stochastic Actor-Oriented Models (SAOM or Siena)
 
Data-Driven Learning Strategy
Data-Driven Learning StrategyData-Driven Learning Strategy
Data-Driven Learning Strategy
 
WAPWG Jan 2020 Sloan cosmos workshop
WAPWG Jan 2020 Sloan cosmos workshopWAPWG Jan 2020 Sloan cosmos workshop
WAPWG Jan 2020 Sloan cosmos workshop
 
Finding prominent features in communities in social networks using ontology
Finding prominent features in communities in social networks using ontologyFinding prominent features in communities in social networks using ontology
Finding prominent features in communities in social networks using ontology
 
Gamification in the Social Environment: a tool for Motivation and Engagement
Gamification in the Social Environment: a tool for Motivation and EngagementGamification in the Social Environment: a tool for Motivation and Engagement
Gamification in the Social Environment: a tool for Motivation and Engagement
 
Social Network Analysis: applications for education research
Social Network Analysis: applications for education researchSocial Network Analysis: applications for education research
Social Network Analysis: applications for education research
 
Contextual Recommendation of Social Updates, a tag-based framework
Contextual Recommendation of Social Updates, a tag-based frameworkContextual Recommendation of Social Updates, a tag-based framework
Contextual Recommendation of Social Updates, a tag-based framework
 
A Meteoroid on Steroids: Ranking Media Items Stemming from Multiple Social Ne...
A Meteoroid on Steroids: Ranking Media Items Stemming from Multiple Social Ne...A Meteoroid on Steroids: Ranking Media Items Stemming from Multiple Social Ne...
A Meteoroid on Steroids: Ranking Media Items Stemming from Multiple Social Ne...
 
Community detection in complex social networks
Community detection in complex social networksCommunity detection in complex social networks
Community detection in complex social networks
 
Social Phrases Having Impact in Altmetrics - SOPHIA
Social Phrases Having Impact in Altmetrics - SOPHIASocial Phrases Having Impact in Altmetrics - SOPHIA
Social Phrases Having Impact in Altmetrics - SOPHIA
 

Mehr von Ismail BADACHE

Prédire l’intensité de contradiction dans les commentaires : faible, forte ou...
Prédire l’intensité de contradiction dans les commentaires : faible, forte ou...Prédire l’intensité de contradiction dans les commentaires : faible, forte ou...
Prédire l’intensité de contradiction dans les commentaires : faible, forte ou...
Ismail BADACHE
 
Intensité de contradiction dans les commentaires (Séminaire à l'EHESS 04 avri...
Intensité de contradiction dans les commentaires (Séminaire à l'EHESS 04 avri...Intensité de contradiction dans les commentaires (Séminaire à l'EHESS 04 avri...
Intensité de contradiction dans les commentaires (Séminaire à l'EHESS 04 avri...
Ismail BADACHE
 
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Ismail BADACHE
 
Finding and Quantifying Temporal-Aware Contradiction in Reviews
Finding and Quantifying Temporal-Aware Contradiction in ReviewsFinding and Quantifying Temporal-Aware Contradiction in Reviews
Finding and Quantifying Temporal-Aware Contradiction in Reviews
Ismail BADACHE
 
Les Signaux Sociaux Émotionnels : Quel impact sur la RI ?
Les Signaux Sociaux Émotionnels : Quel impact sur la RI ? Les Signaux Sociaux Émotionnels : Quel impact sur la RI ?
Les Signaux Sociaux Émotionnels : Quel impact sur la RI ?
Ismail BADACHE
 
Détection de contradiction dans les commentaires
Détection de contradiction dans les commentairesDétection de contradiction dans les commentaires
Détection de contradiction dans les commentaires
Ismail BADACHE
 
Pertinence a Priori Basée sur la Diversité et la Temporalité des Signaux Sociaux
Pertinence a Priori Basée sur la Diversité et la Temporalité des Signaux SociauxPertinence a Priori Basée sur la Diversité et la Temporalité des Signaux Sociaux
Pertinence a Priori Basée sur la Diversité et la Temporalité des Signaux Sociaux
Ismail BADACHE
 
Poster Recherche d'Information Sociale
Poster Recherche d'Information SocialePoster Recherche d'Information Sociale
Poster Recherche d'Information Sociale
Ismail BADACHE
 

Mehr von Ismail BADACHE (16)

Recherche d'Information Sociale en Langue Arabe : Cas de Facebook
Recherche d'Information Sociale en Langue Arabe : Cas de FacebookRecherche d'Information Sociale en Langue Arabe : Cas de Facebook
Recherche d'Information Sociale en Langue Arabe : Cas de Facebook
 
Predicting Contradiction Intensity: Low, Strong or Very Strong?
Predicting Contradiction Intensity: Low, Strong or Very Strong?Predicting Contradiction Intensity: Low, Strong or Very Strong?
Predicting Contradiction Intensity: Low, Strong or Very Strong?
 
Prédire l’intensité de contradiction dans les commentaires : faible, forte ou...
Prédire l’intensité de contradiction dans les commentaires : faible, forte ou...Prédire l’intensité de contradiction dans les commentaires : faible, forte ou...
Prédire l’intensité de contradiction dans les commentaires : faible, forte ou...
 
Intensité de contradiction dans les commentaires (Séminaire à l'EHESS 04 avri...
Intensité de contradiction dans les commentaires (Séminaire à l'EHESS 04 avri...Intensité de contradiction dans les commentaires (Séminaire à l'EHESS 04 avri...
Intensité de contradiction dans les commentaires (Séminaire à l'EHESS 04 avri...
 
Contradiction in Reviews: is it Strong or Low?
Contradiction in Reviews: is it Strong or Low?Contradiction in Reviews: is it Strong or Low?
Contradiction in Reviews: is it Strong or Low?
 
LES CONTENUS SOCIAUX : Quel impact sur le processus de RI et la quantificatio...
LES CONTENUS SOCIAUX : Quel impact sur le processus de RI et la quantificatio...LES CONTENUS SOCIAUX : Quel impact sur le processus de RI et la quantificatio...
LES CONTENUS SOCIAUX : Quel impact sur le processus de RI et la quantificatio...
 
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
Harnessing Ratings and Aspect-Sentiment to Estimate Contradiction Intensity i...
 
Finding and Quantifying Temporal-Aware Contradiction in Reviews
Finding and Quantifying Temporal-Aware Contradiction in ReviewsFinding and Quantifying Temporal-Aware Contradiction in Reviews
Finding and Quantifying Temporal-Aware Contradiction in Reviews
 
Les Signaux Sociaux Émotionnels : Quel impact sur la RI ?
Les Signaux Sociaux Émotionnels : Quel impact sur la RI ? Les Signaux Sociaux Émotionnels : Quel impact sur la RI ?
Les Signaux Sociaux Émotionnels : Quel impact sur la RI ?
 
Détection de contradiction dans les commentaires
Détection de contradiction dans les commentairesDétection de contradiction dans les commentaires
Détection de contradiction dans les commentaires
 
Social Signals: Any Impacts in Search?
Social Signals: Any Impacts in Search?Social Signals: Any Impacts in Search?
Social Signals: Any Impacts in Search?
 
Multimodal Social Book Search
Multimodal Social Book SearchMultimodal Social Book Search
Multimodal Social Book Search
 
Pertinence a Priori Basée sur la Diversité et la Temporalité des Signaux Sociaux
Pertinence a Priori Basée sur la Diversité et la Temporalité des Signaux SociauxPertinence a Priori Basée sur la Diversité et la Temporalité des Signaux Sociaux
Pertinence a Priori Basée sur la Diversité et la Temporalité des Signaux Sociaux
 
Social Networks Statistics 2014
Social Networks Statistics 2014Social Networks Statistics 2014
Social Networks Statistics 2014
 
Exploitation de signaux sociaux pour estimer la pertinence a priori d’une res...
Exploitation de signaux sociaux pour estimer la pertinence a priori d’une res...Exploitation de signaux sociaux pour estimer la pertinence a priori d’une res...
Exploitation de signaux sociaux pour estimer la pertinence a priori d’une res...
 
Poster Recherche d'Information Sociale
Poster Recherche d'Information SocialePoster Recherche d'Information Sociale
Poster Recherche d'Information Sociale
 

Kürzlich hochgeladen

Capstone slidedeck for my capstone project part 2.pdf
Capstone slidedeck for my capstone project part 2.pdfCapstone slidedeck for my capstone project part 2.pdf
Capstone slidedeck for my capstone project part 2.pdf
eliklein8
 
Call Girls in Chattarpur (delhi) call me [9953056974] escort service 24X7
Call Girls in Chattarpur (delhi) call me [9953056974] escort service 24X7Call Girls in Chattarpur (delhi) call me [9953056974] escort service 24X7
Call Girls in Chattarpur (delhi) call me [9953056974] escort service 24X7
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Capstone slidedeck for my capstone final edition.pdf
Capstone slidedeck for my capstone final edition.pdfCapstone slidedeck for my capstone final edition.pdf
Capstone slidedeck for my capstone final edition.pdf
eliklein8
 

Kürzlich hochgeladen (20)

Film the city investagation powerpoint :)
Film the city investagation powerpoint :)Film the city investagation powerpoint :)
Film the city investagation powerpoint :)
 
BDSM⚡Call Girls in Sector 76 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 76 Noida Escorts >༒8448380779 Escort ServiceBDSM⚡Call Girls in Sector 76 Noida Escorts >༒8448380779 Escort Service
BDSM⚡Call Girls in Sector 76 Noida Escorts >༒8448380779 Escort Service
 
Film show investigation powerpoint for the site
Film show investigation powerpoint for the siteFilm show investigation powerpoint for the site
Film show investigation powerpoint for the site
 
SEO Expert in USA - 5 Ways to Improve Your Local Ranking - Macaw Digital.pdf
SEO Expert in USA - 5 Ways to Improve Your Local Ranking - Macaw Digital.pdfSEO Expert in USA - 5 Ways to Improve Your Local Ranking - Macaw Digital.pdf
SEO Expert in USA - 5 Ways to Improve Your Local Ranking - Macaw Digital.pdf
 
Production diary Film the city powerpoint
Production diary Film the city powerpointProduction diary Film the city powerpoint
Production diary Film the city powerpoint
 
Generate easy money from tiktok using this simple steps on the book.
Generate easy money from tiktok using this simple steps on the book.Generate easy money from tiktok using this simple steps on the book.
Generate easy money from tiktok using this simple steps on the book.
 
Film show evaluation powerpoint for site
Film show evaluation powerpoint for siteFilm show evaluation powerpoint for site
Film show evaluation powerpoint for site
 
Capstone slidedeck for my capstone project part 2.pdf
Capstone slidedeck for my capstone project part 2.pdfCapstone slidedeck for my capstone project part 2.pdf
Capstone slidedeck for my capstone project part 2.pdf
 
Capstone slide deck on the TikTok revolution
Capstone slide deck on the TikTok revolutionCapstone slide deck on the TikTok revolution
Capstone slide deck on the TikTok revolution
 
Ignite Your Online Influence: Sociocosmos - Where Social Media Magic Happens
Ignite Your Online Influence: Sociocosmos - Where Social Media Magic HappensIgnite Your Online Influence: Sociocosmos - Where Social Media Magic Happens
Ignite Your Online Influence: Sociocosmos - Where Social Media Magic Happens
 
Call Girls in Chattarpur (delhi) call me [9953056974] escort service 24X7
Call Girls in Chattarpur (delhi) call me [9953056974] escort service 24X7Call Girls in Chattarpur (delhi) call me [9953056974] escort service 24X7
Call Girls in Chattarpur (delhi) call me [9953056974] escort service 24X7
 
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
Unlock the power of Instagram with SocioCosmos. Start your journey towards so...
 
Improve Your Brand in Waco with a Professional Social Media Marketing Company
Improve Your Brand in Waco with a Professional Social Media Marketing CompanyImprove Your Brand in Waco with a Professional Social Media Marketing Company
Improve Your Brand in Waco with a Professional Social Media Marketing Company
 
Capstone slidedeck for my capstone final edition.pdf
Capstone slidedeck for my capstone final edition.pdfCapstone slidedeck for my capstone final edition.pdf
Capstone slidedeck for my capstone final edition.pdf
 
Film show post-production powerpoint for site
Film show post-production powerpoint for siteFilm show post-production powerpoint for site
Film show post-production powerpoint for site
 
Hire↠Young Call Girls in Hari Nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esco...
Hire↠Young Call Girls in Hari Nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esco...Hire↠Young Call Girls in Hari Nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esco...
Hire↠Young Call Girls in Hari Nagar (Delhi) ☎️ 9205541914 ☎️ Independent Esco...
 
Enjoy Night⚡Call Girls Palam Vihar Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Palam Vihar Gurgaon >༒8448380779 Escort ServiceEnjoy Night⚡Call Girls Palam Vihar Gurgaon >༒8448380779 Escort Service
Enjoy Night⚡Call Girls Palam Vihar Gurgaon >༒8448380779 Escort Service
 
The Butterfly Effect
The Butterfly EffectThe Butterfly Effect
The Butterfly Effect
 
Film show pre-production powerpoint for site
Film show pre-production powerpoint for siteFilm show pre-production powerpoint for site
Film show pre-production powerpoint for site
 
Social media marketing/Seo expert and digital marketing
Social media marketing/Seo expert and digital marketingSocial media marketing/Seo expert and digital marketing
Social media marketing/Seo expert and digital marketing
 

Harnessing social signals to enhance a search

  • 1. Ismaïl BADACHE, Mohand BOUGHANEM IRIT, Toulouse University, France {badache, boughanem}@irit.fr Warsaw, Poland
  • 2. Presentation Plan Introduction Related Work Approach of Social Information Retrieval Experimental Results4 1 3 Conclusion 2 5
  • 3. 1.1 Emergence of social Web 1 Number of active users 2013 1,2 1,4 1,7 2,4 2011 2012 2013 2014 Number of Internet users Social content per 1 minute 41000 Publications 1,8 Million Like ~350 GB of Data Facebook Source: blogdumoderateur.com quantcast.com semiocast.com 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results
  • 4. Video Photo Web Page Web Resources Resource . . . Social Networks Bookmark Comment Share/Recommend Motion/Vote Like/+1 Interaction Extraction and quantification of social properties Information Retrieval Model (Ranking) Integration Query 2 Results Fig 1. Global presentation of our work Social Signals (Source of Evidence) Popularity Reputation Freshness
  • 5. 3 1.2 Example of Social Signals 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results
  • 6. 1.3 Research Issues Can these social data help the search systems for guiding the users to reach a better quality or more relevant content? 2 How effective is each individual social signal for ranking resources for a given query? What are the ranking correlations created by these social data? 3 4 How to combine these social data in form of social properties? What are the most useful of them to take into account in a model search? 4 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results 1 What happens when a user clicks on like or dislike button or posts a comment for a resource, say a Web page, photo or video?
  • 7. Sources of evidence (Social Features) Properties Models Authors • Number of : clicks, votes, records and recommendations. Popularity Importance Linear combination (Karweg et al., 2011) • Number of : like, dislike, comments on YouTube. • The playcount (number of times a user listens to a track on lastfm) Importance Machine learning and Linear combination (Chelaru et al., 2012) (Khodaei et al. 2012) • Presence of a URL in a tweet. (Alonso et al., 2010) • Number of retweets. • Number of annotations (tags). Popularity Machine learning (Yang et al., 2012) (Hong et al., 2011) (Pantel et al., 2012) 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results 2.1 Related Work 5
  • 8. • Our IR approach consists of exploiting various and heterogeneous social signals from different social networks to define social properties to take into account in retrieval model. We associate to each Web resource a priori relevance based on these social properties. This relevance is then combined with a classical topical relevance. 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results 3.1 A Modular Approach for Social IR 6
  • 9. • We assume that resource r can be represented both by a set of textual key-words 𝑟𝑤={𝑤1, 𝑤2, … 𝑤 𝑛} and a set of social actions (signals) performed on this resource, 𝑟𝑎={𝑎1, 𝑎2, … 𝑎 𝑚}. • We consider a set X={Popularity, Reputation, Freshness} of 3 social properties that characterize a resource r. Each property is quantified by a specific actions group. These properties are considered as a priori knowledge of a resource. 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results 3.2 Social Signals and Social Properties 7 Web Resource - Textual key-words - Social Signals - Like - +1 - Share - Comment - Dates of actions Web Resource - Textual key-words - Social Signals - Like - +1 - Share - Comment - Dates of actions Reputation Popularity Freshness
  • 10. 𝑓𝑥 𝑟, 𝐺 = 𝑖=1, 𝑎 𝑖 𝑥 ∈ 𝐴 𝑚 𝐶𝑜𝑢𝑛𝑡 (𝑎𝑖 𝑥 , 𝑟, 𝐺) 3.1 Proposed Approach • Popularity: The resource popularity can be estimated according to the rate of sharing this resource on social networks. • Reputation: The resource reputation can be estimated based on social activities that have positive meaning such as Facebook like. Indeed, resource reputation depends on the degree of users' appreciation on social networks. The general formula is the following: 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results 3.3 Estimation of Popularity and Reputation 8 𝑓𝑥(𝑟, 𝐺) 𝑁𝑜𝑟𝑚= 𝑓𝑥 𝑟, 𝐺 − 𝑀𝐼𝑁(𝑓𝑥 𝑟, 𝐺 ) 𝑀𝐴𝑋 𝑓𝑥 𝑟, 𝐺 − 𝑀𝐼𝑁(𝑓𝑥 𝑟, 𝐺 ) (1) (2)
  • 11. 3.1 Proposed Approach • Let 𝑇𝑎 𝑖 ={𝑡1,𝑎 𝑖 , 𝑡2,𝑎 𝑖 , … 𝑡 𝑘,𝑎 𝑖 } a set of k moments (date) at which action 𝑎𝑖 was produced. A moment t represents the datetime for each action a of the same type. • Freshness: We assume that a resource is fresh if recent social signals were associated with it. For that purpose, we define freshness as follows: "a date of each social action (e.g., date of comment, date of share) performed on a resource on social networks can be exploited to measure the recency of these social actions, hence the freshness of information". Its formula is the following: 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results 3.4 Estimation of Freshness 9 𝑓𝐹 𝑟, 𝐺 = 1 1 𝑚 𝑖=1 𝑚 ( 1 𝑘 𝑗=1 𝑘 𝑇𝑖𝑚𝑒(𝑡𝑗,𝑎 𝑖 , 𝑟, 𝐺)) (3)
  • 12. 3.1 Proposed Approach • The combination of topical relevance with social relevance is given by the following formula: • Social Score: Regarding the social score 𝑅𝑒𝑙 𝑆(𝑞, 𝑟, 𝐺), we specify that this score takes into account these social properties, which are in the form of three normalized factors that are combined linearly by the following formula: 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results Score of Topical Relevance Score of Social Relevance 𝑅𝑒𝑙 𝑞, 𝑟, 𝐺 = α ∙ 𝑅𝑒𝑙 𝑇(𝑞, 𝑟) + (1 - α) ∙ 𝑅𝑒𝑙 𝑆(𝑞, 𝑟, 𝐺) Freshness 𝑅𝑒𝑙 𝑆 𝑞, 𝑟, 𝐺 = β ∙ 𝑓𝐹(𝑟, 𝐺) + λ ∙ 𝑓𝑃(𝑟, 𝐺) + δ ∙ 𝑓𝑅(𝑟, 𝐺) Popularity Reputation 3.5 First Method : Linear Combination 10 (4) (5)
  • 13. 3.1 Proposed Approach 1. Introduction 2. Related Work 5. Conclusion 3. Approach of SIR 4. Experimental Results 3.6 Second Method : Machine Learning Models 11 Original Dataset Training Dataset Attribute Selection Algorithms - WrapperSubsetEval1 - CfsSubsetEval1 - ReliefFAttributeEval2 - SVMAttributeEval3 Learning Algorithms - Naïve Bayes1 - J482 - SVM3 Cross-Fold Evaluation Repeat 5 x for 5-Fold Cross Validation Fig 2. Machine Learning Process Topical model results for all topics
  • 14. 3.1 Proposed Approach • Objectives 1. Studying the impact of each individual integration of social signals on the performance of retrieval process. 2. Studying the impact of combining these social signals as social properties. 3. Studying the ranking correlation between social signals and relevance. • Evaluation challenge 1. Absence of a standard framework for evaluation in social IR. 2. Collect social signals from 5 social networks and mount experimentation. 1. Introduction 2. Related Work 5. Conclusion 4.1 Experimental Evaluation 12 3. Approach of SIR 4. Experimental Results
  • 15. 3.1 Proposed Approach • Textual Content: 32706 Documents Film in English extracted from IMDb. • Social Content: 8 social data from 5 social networks. 1. Introduction 2. Related Work 5. Conclusion 4.2 Description of DataSet 13 3. Approach of SIR 4. Experimental Results ID Title Year Released Runtime Genre Director Writer Actors Plot Poster url - indexed indexed indexed indexed indexed indexed indexed indexed indexed - - ACEBOOK Like Share Comment Date of last action WITTER Tweet GOOGLE+ +1 Share LINKEDDELICIOUS Bookmark
  • 16. 3.1 Proposed Approach 1. Introduction 2. Related Work 5. Conclusion 4.3 Quantifying of Social Properties 14 3. Approach of SIR 4. Experimental Results Social Properties Social Signals Social Networks Popularity P Number of « Comment » C1 Facebook Number of « Tweet » C2 Twitter Number of « Share » C3 LinkedIn Number of « Share » C4 Facebook Reputation R Number of « Like » C5 Google+ Number of « +1 » C6 Facebook Number of « Bookmark » C7 Delicious Freshness F Date of last action C8 Facebook • Each social property is quantified based on social signals according to their nature and signification.
  • 17. 3.1 Proposed Approach 1. Introduction 2. Related Work 5. Conclusion 4.4 Results: Linear Combination 15 3. Approach of SIR 4. Experimental Results 0 0,1 0,2 0,3 0,4 0,5 0,6 Like Share Comment Tweet Mention+1 Share(LIn) Bookmark Individual Integration of Social Signals 0 0,1 0,2 0,3 0,4 0,5 0,6 0,7 Freshness F Reputation R Popularity P R+F P+F P+R All Properties Different Combinations of Social Signals (Social Properties) 0 0,1 0,2 0,3 0,4 BM25 Lucene Model Baselines (Topical Models) P@10 P@20 nDCG@10 nDCG@20 Facebook signals
  • 18. 3.1 Proposed Approach 1. Introduction 2. Related Work 5. Conclusion 4.5 Results: Machine Learning 16 3. Approach of SIR 4. Experimental Results Table 1. Selected Social Signals With Attribute Selection Algorithms ++ : Highly selected + : Moderately selected
  • 19. 3.1 Proposed Approach 1. Introduction 2. Related Work 5. Conclusion 4.5 Results: Machine Learning 17 3. Approach of SIR 4. Experimental Results Naïve Bayes SVM J48 P@20 0,5105 0,5131 0,689 0,5105 0,5131 0,689 0 0,1 0,2 0,3 0,4 0,5 0,6 0,7 0,8 Naïve Bayes (CFS) Naïve Bayes (WRP) SVM (SVM) J48 (RLF) P@20 0,5315 0,5105 0,5131 0,689 0,5315 0,5105 0,5131 0,689 0 0,1 0,2 0,3 0,4 0,5 0,6 0,7 0,8 Machine learning results with using Attribute Selection Algorithms Machine learning without using Attribute Selection Algorithms
  • 20. 3.1 Proposed Approach 1. Introduction 2. Related Work 5. Conclusion 4.6 Results: Ranking Correlation Analysis 18 3. Approach of SIR 4. Experimental Results Fig 3. Spearman correlation between social signals and relevance Fig 4. Spearman correlation between social properties and relevance
  • 21. 3.1 Proposed Approach 1. Introduction 2. Related Work 5. Conclusion 5. Conclusion 19 3. Proposed Approaches 4. Experimental Results • Social Information Retrieval Model - Topical relevance (retrieval model based content only). - Social relevance (retrieval model based content and social features). - Attribute selection algorithms and machine learning. • Experimental Evaluation - Superiority of proposed approach compared to textual models (baselines). - Positive ranking correlation between social signals and relevance. • Perspectives - Integration of other social features. - Further study on the impact of the temporal property. - Comparison of the proposed models with other social models. - Experimental evaluation on larger dataset.