SlideShare a Scribd company logo
1 of 37
Download to read offline
ENTER 2017 Research Track Slide Number 1
Christoph Grün, Julia Neidhardt*), Hannes Werthner
E-Commerce Group, TU Wien, Austria
*) julia.neidhardt@ec.tuwien.ac.at
http://www.ec.tuwien.ac.at
Ontology-based Matchmaking to
Provide Personalized Offers
ENTER 2017 Research Track Slide Number 2
Agenda
 Problem Statement
 Related Work
 Matchmaking Process
 Implementation
 Evaluation
 Conclusion & Future Work
→
→
→
→
→
→
ENTER 2017 Research Track Slide Number 3
Problem Statement
ENTER 2017 Research Track Slide Number 4
Problem Statement
No common view on the tourism space exists
 Gap between mental model of tourists and model of tourism
offers/space (Gretzel et al.*))
 Problem: matching of the customers’ view (tourist’s personality and
preferences) with the suppliers’ perspective (tourism objects)
 Approach: ontology-based matchmaking process
 Focus of this talk: present results of a user study focusing on
evaluating the feasibility of the approach
*) Gretzel et al. Semantic Representation of Tourism on the Internet. Journal of Travel Research, 2008.
→
→
→
→
matching
ENTER 2017 Research Track Slide Number 5
Related Work
ENTER 2017 Research Track Slide Number 6
Recommendation
Systems
Types of
Recommenders
Tourist Typologies
Semantic Web
Ontologies Similarities
MTRS
Gavalas & Kenteris,
2011
SPETA
García-Crespo et al.,
2009
Advisor Suite
Jananch et al., 2010
etPlanner
Höpken et al., 2006
SigTur
Moreno et al., 2012
PixMeAway
Neidhardt et al., 2014
Demographic-
based
Burke, 2007
Collaborative-
based
Herlocker et al.,
2004
Content-based
Pazzani & Billsus,
2007
Knowledge-based
Felfernig et al.,
2006
Hybrid
Recommenders
Schiaffino &
Amandi, 2009
Characteristics and
motivation of
tourists
Cohen, 1972
Tourist Roles
Yiannakis & Gibson,
1992
Model of a
destination’s
attractiveness
Plog, 2001
Travel career
patterns
Pearce & Lee, 2005
Tourist Factors
Neidhardt et al., 2014
QALL-ME
Ou et al., 2008
CRUZAR
Mínguez et al.,
2010
SPETA
García-Crespo
et al., 2009
INREDIS
Busquet, 2009
HARMONISE
Fodor &
Werthner, 2005
GETESS
Staab et al.,
1999
Path-based
Rada et al., 1989
Wu & Palmer,
1994
Zhong et al.,
2002
Sussna, 1993
Information-
based
Resnik, 1998
Seco et al., 2004
Feature-based
Tversky, 1977
Knappe et al.,
2007
Hybrid
Jiang & Conrath,
1997
Lian, 1998
Mazuel et al.,
2008
Related Work
The research draws on knowledge from different fields
ENTER 2017 Research Track Slide Number 7
Matchmaking Process
ENTER 2017 Research Track Slide Number 8
Matchmaking Process
The matchmaking comprises two sub-processes
Tourist Types
Tourist Tourism Object
Generic
Preferences
Generic
Characteristics
PROCESS1
PROCESS 1 PROCESS 2
ENTER 2017 Research Track Slide Number 9
Matchmaking Process
The matchmaking comprises two sub-processes
Tourist Types
Tourist Tourism Object
Generic
Preferences
Generic
Characteristics
PROCESS1
MATCHMAKING
PROCESS 1 PROCESS 2
ENTER 2017 Research Track Slide Number 10
Tourist
Matchmaking Process
The matchmaking comprises two sub-processes
Tourist Types
Tourist Tourism Object
Generic
Preferences
Generic
Characteristics
PROCESS1PROCESS2
Specific
Interests
Top N
Recommendations
MATCHMAKING
PROCESS 1 PROCESS 2
ENTER 2017 Research Track Slide Number 11
Tourist
Matchmaking Process
The matchmaking comprises two sub-processes
Tourist Types
Tourist Tourism Object
Generic
Preferences
Generic
Characteristics
PROCESS1PROCESS2
Specific
Interests
Top N
Recommendations
MATCHMAKING
PROCESS 1 PROCESS 2
ENTER 2017 Research Track Slide Number 12
Tourist
Matchmaking Process
The matchmaking comprises two sub-processes
Tourist Types
Tourist Tourism Object
Generic
Preferences
Generic
Characteristics
PROCESS1PROCESS2
Specific
Interests
Learn specific interests’dislike churches’
MATCHMAKING
PROCESS 1 PROCESS 2
Specific
Interests
ENTER 2017 Research Track Slide Number 13
Tourist
Matchmaking Process
The matchmaking comprises two sub-processes
Tourist Types
Tourist Tourism Object
Generic
Preferences
Generic
Characteristics
PROCESS1PROCESS2
Tourism Object
Specific
Attributes
Learn specific interests’dislike churches’
MATCHMAKING
PROCESS 1 PROCESS 2
Specific
Interests
ENTER 2017 Research Track Slide Number 14
Matchmaking Process
The matchmaking comprises two sub-processes
Tourist Types
Tourist Tourism Object
Generic
Preferences
Generic
Characteristics
PROCESS1PROCESS2
Tourist Tourism Object
Specific
Interests
Specific
Attributes
Learn specific interests’dislike churches’
MATCHMAKING
MATCHMAKING
Tourism Ontology
PROCESS 1 PROCESS 2
ENTER 2017 Research Track Slide Number 15
 Fragment of the cDOTT*) ontology depicting the semantic description
of the Viennese attraction Schönbrunn Palace
Matchmaking Process
A tourism ontology is used to drive the matchmaking
→
PROCESS 1 PROCESS 2
*) cDOTT = core Domain Ontology of Travel and Tourism
Barta et al. Covering the semantic space of tourism: An approach based on modularized ontologies. In
Proceedings of the 1st Workshop on Context, Information and Ontologies, 2009.
ENTER 2017 Research Track Slide Number 16
 Tourist types are a valid means to predict the set of activities in
which tourist like to engage*).
 We use the 7 tourist factors (e.g. culture loving) presented by
Neidhardt et al.**)
 Predefined tourist factors can be used as stereotypical
approach to generate a generic profile
 Orthogonal vectors are suited to model tourist factors
Tourist
Generic
Preferences
First Matchmaking Process
Generating a high-level tourist profile
Tourist Types
*) Gretzel et al. Tell me who you are and I will tell you where to go: Use of Travel Personalities in Destination
Recommendation Systems. Information Technology & Tourism, 7:3– 12, 2004.
**) Neidhardt et al. A picture-based approach to recommender systems. Information Technology & Tourism, 15(1), 2014.
→
PROCESS 1 PROCESS 2
→
→
→
Sight Seeker
Cultural Visitor
Nature Lover
Avid AthletheAction Seeker
Educational Buff
Sun Worshipper
PROCESS1
ENTER 2017 Research Track Slide Number 17
Tourist
Second Matchmaking Process
Exploit ratings to learn specific interests of tourist
Tourist TypesPROCESS2
Specific
Interests
Learn specific interests
Specific
Interests
’dislike churches’
PROCESS 1 PROCESS 2
Tourist Tourism Object
PROCESS1
MATCHMAKING
Sight Seeker
Cultural Visitor
Nature Lover
Avid AthletheAction Seeker
Educational Buff
Sun Worshipper
Sight Seeker
Cultural Visitor
Nature Lover
Avid AthletheAction Seeker
Educational Buff
Sun Worshipper
ENTER 2017 Research Track Slide Number 18
Tourist
Second Matchmaking Process
Exploit ratings to learn specific interests of tourist
Tourist TypesPROCESS2
Specific
Interests
Learn specific interests
Tourism Object
Specific
Interests
Specific
Attributes
’dislike churches’
PROCESS 1 PROCESS 2
Tourist Tourism Object
PROCESS1
MATCHMAKING
Sight Seeker
Cultural Visitor
Nature Lover
Avid AthletheAction Seeker
Educational Buff
Sun Worshipper
Sight Seeker
Cultural Visitor
Nature Lover
Avid AthletheAction Seeker
Educational Buff
Sun Worshipper
ENTER 2017 Research Track Slide Number 19
Tourist
Second Matchmaking Process
Exploit ratings to learn specific interests of tourist
Tourist TypesPROCESS2
Specific
Interests
Learn specific interests
Tourism Object
Specific
Interests
Specific
Attributes
Tourism Ontology
’dislike churches’
PROCESS 1 PROCESS 2
Tourist Tourism Object
PROCESS1
MATCHMAKING
Sight Seeker
Cultural Visitor
Nature Lover
Avid AthletheAction Seeker
Educational Buff
Sun Worshipper
Sight Seeker
Cultural Visitor
Nature Lover
Avid AthletheAction Seeker
Educational Buff
Sun Worshipper
ENTER 2017 Research Track Slide Number 20
 Ratings of objects are used to learn the tourist’s specific interests
 The specific interests are represented as an overlay of the
ontological model
Second Matchmaking Process
Using an ontology-based approach to model the profile
Tourist
Specific
Interests
→
→
PROCESS 1 PROCESS 2
PROCESS2
Imperial Furniture Collection
Identify leaf concepts that describe object
Assign numerical score to the leaf concepts
Exploit ontological hierarchy to infer interest
score for super-concepts (spreading activation)
using a propagation function following Sieg et
al., 2007.
1
2
3
Sieg et al. Web search personalization with ontological user profiles.
In CIKM ’07: Proceedings of the sixteenth ACM conference on Conference
on information and knowledge management, 2007.
Ontology
Concept(
Concept(Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(Concept(Concept(Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(
Concept(Concept(
ENTER 2017 Research Track Slide Number 21
Implementation
ENTER 2017 Research Track Slide Number 22
Prototype for the
City of Vienna
ENTER 2017 Research Track Slide Number 23
Recommended
tourism objects
ENTER 2017 Research Track Slide Number 24
Detailed description
of a tourism object
ENTER 2017 Research Track Slide Number 25
Evaluation
ENTER 2017 Research Track Slide Number 26
Evaluation
54 users completed the questionnaire
 Period of 3 months from June to September 2015
 Target group
 Tourists who visited or plan to visit Vienna in near future
 Persons who know this city well (live or work here)
 User sessions identified from Weblog information
 70 users started to fill out questionnaire
 54 users completed the questionnaire → final dataset
Age distribution of users within final dataset (n=54)
→
→
→
ENTER 2017 Research Track Slide Number 27
Evaluation
Users identify themselves with a mixture of factors
 Participants identify themselves with a mixture of all 7 factors
 about 75% chose at least 5 factors → users tend to select more than
1 tourist factor if they have the choice
 The factors Sight Seeker, Cultural Visitor and Nature Lover were
most often selected → Vienna is a city destination
1
1
Number of factors selected by the users (n=54) Distribution of the tourist factors on average (n=54)
2
2
→
ENTER 2017 Research Track Slide Number 28
Evaluation
50% of the users executed 1-3 recommendation cycles
 This figure shows the number of recommendation cycles
 About 70% of the users explored the recommendations proposed by the
system within 1 to 6 recommendation cycles
 The median has the value 3 → 50% of the users executed 1-3 cycles
1
2
1
2
→
(n=54)
ENTER 2017 Research Track Slide Number 29
Evaluation
 About 75% of the objects were added in the first 3 cycles to the favourites
 On average, 8.5 ratings had been given in each user session (ca. 5.3
positive and 3.2 negative ratings), 40% ratings were stated in the 1 cycle
→
→
ENTER 2017 Research Track Slide Number 30
Evaluation
Measuring the relevance of the recommendations
 As in our case no dataset is available, we decided to
 show the users 10 objects that were randomly chosen from the whole
dataset and had not been recommended before
 let them decide if one or more objects are relevant for them
(by adding them to the top-N list)
About 70 % of the users added at maximum 1 of the randomly shown object
to their favorites
→
Feedback from the users to the randomly shown objects, n=54
this might be an indication that they were quite satisfied with the
recommendations
Why had these objects not been recommended before?
• Object is related to a tourist factor not selected by the user
• Other objects of same category already recommended
• Objects of other categories positively rated → user profile more aligned with
profiles of those objects
1
2
→
ENTER 2017 Research Track Slide Number 31
Evaluation
Participants’ feedback
 Information collected from the questionnaire→
ENTER 2017 Research Track Slide Number 32
Conclusion & Future Work
ENTER 2017 Research Track Slide Number 33
Conclusion & Future Work
 The goal was to close the gap between users’ needs and
suppliers’ perspective by developing a matchmaking process
 A Web-based prototype was implemented for the city Vienna
 A first evaluation was conducted which aimed to investigate the
feasibility of the approach
 Overall, the evaluation shows that the two-step matchmaking
process and the feedback cycle work
 In future we will define automated procedures to annotate the
tourism objects semantically
→
→
→
→
→
Thank youThank you
ENTER 2017 Research Track Slide Number 35
Appendix
ENTER 2017 Research Track Slide Number 36
Evaluation
Correlation between the tourist factors
ENTER 2017 Research Track Slide Number 37
With score propagation
Evaluation
Score propagation improves recommendations
 Propagation of user interests within the semantic model affects
the position of relevant tourism objects in the Top-N list
Without score propagation
3
• Objects might be relevant but not included in Top-N list3
ghotic/romanesque
architecturestyle
2
• On the next positions are 4 churches as they belong to
the «ghotic/architeture» style as «St. Stephen‘s Cathedral»
2
Positive Rating of
St. Stephen’s
Cathedral
• Positive rating «St. Stephen‘s Cathedral»1
1
• Objects are now directly placed on subsequent
positions within the list. Due to score propagation
in the semantic model, the user profile gets more
similar to the profiles of the objects (larger overlap)
2
2
Positive Rating of
St. Stephen’s
Cathedral
• Positive rating «St. Stephen‘s Cathedral» → first
position
1
1
→

More Related Content

Viewers also liked

Viewers also liked (20)

Duetto: An introduction to Revenue Judo
Duetto: An introduction to Revenue JudoDuetto: An introduction to Revenue Judo
Duetto: An introduction to Revenue Judo
 
Predicting Tourism Demand Using Big Data - Issues and Challenges
Predicting Tourism Demand Using Big Data - Issues and ChallengesPredicting Tourism Demand Using Big Data - Issues and Challenges
Predicting Tourism Demand Using Big Data - Issues and Challenges
 
How do we search? Themes and challenges
How do we search? Themes and challengesHow do we search? Themes and challenges
How do we search? Themes and challenges
 
Can we predict your sentiments by listening to your peers?
Can we predict your sentiments by listening to your peers?Can we predict your sentiments by listening to your peers?
Can we predict your sentiments by listening to your peers?
 
DFRC from data to knowledge. Learn from your data. Measure, Manage, Innovate,...
DFRC from data to knowledge. Learn from your data. Measure, Manage, Innovate,...DFRC from data to knowledge. Learn from your data. Measure, Manage, Innovate,...
DFRC from data to knowledge. Learn from your data. Measure, Manage, Innovate,...
 
Destination image gaps between official tourism websites and user-generated c...
Destination image gaps between official tourism websites and user-generated c...Destination image gaps between official tourism websites and user-generated c...
Destination image gaps between official tourism websites and user-generated c...
 
Trends in travel agencies' e business perspectives of human resource sector
Trends in travel agencies' e business perspectives of human resource sectorTrends in travel agencies' e business perspectives of human resource sector
Trends in travel agencies' e business perspectives of human resource sector
 
Tracking tourist spatial-temporal behavior in urban places, a methodological ...
Tracking tourist spatial-temporal behavior in urban places, a methodological ...Tracking tourist spatial-temporal behavior in urban places, a methodological ...
Tracking tourist spatial-temporal behavior in urban places, a methodological ...
 
Seekda: Company overview
Seekda: Company overviewSeekda: Company overview
Seekda: Company overview
 
Users creativity in mobile computing travel platforms
Users creativity in mobile computing travel platformsUsers creativity in mobile computing travel platforms
Users creativity in mobile computing travel platforms
 
Exploring the roles of hosts' attachment and psychological ownership in an Ai...
Exploring the roles of hosts' attachment and psychological ownership in an Ai...Exploring the roles of hosts' attachment and psychological ownership in an Ai...
Exploring the roles of hosts' attachment and psychological ownership in an Ai...
 
The use of social media and its impacts on consumer behavior: the context of ...
The use of social media and its impacts on consumer behavior: the context of ...The use of social media and its impacts on consumer behavior: the context of ...
The use of social media and its impacts on consumer behavior: the context of ...
 
Social CRM capabilities and readiness: findings from Greek tourism firms
Social CRM capabilities and readiness: findings from Greek tourism firmsSocial CRM capabilities and readiness: findings from Greek tourism firms
Social CRM capabilities and readiness: findings from Greek tourism firms
 
An exploration of user-driven assessments of travel enhancing apps
An exploration of user-driven assessments of travel enhancing appsAn exploration of user-driven assessments of travel enhancing apps
An exploration of user-driven assessments of travel enhancing apps
 
Surving and thriving in your early academic career
Surving and thriving in your early academic careerSurving and thriving in your early academic career
Surving and thriving in your early academic career
 
Airbnb empowering places
Airbnb empowering placesAirbnb empowering places
Airbnb empowering places
 
To Catch Them All - The (Un)internded Consequences of Pokémon GO on Mobility,...
To Catch Them All - The (Un)internded Consequences of Pokémon GO on Mobility,...To Catch Them All - The (Un)internded Consequences of Pokémon GO on Mobility,...
To Catch Them All - The (Un)internded Consequences of Pokémon GO on Mobility,...
 
The co-creation process of the online image of an Italian World Heritage Site...
The co-creation process of the online image of an Italian World Heritage Site...The co-creation process of the online image of an Italian World Heritage Site...
The co-creation process of the online image of an Italian World Heritage Site...
 
Tourist Acceptance of Augmented Reality Application in Langkawi Geopark, Mala...
Tourist Acceptance of Augmented Reality Application in Langkawi Geopark, Mala...Tourist Acceptance of Augmented Reality Application in Langkawi Geopark, Mala...
Tourist Acceptance of Augmented Reality Application in Langkawi Geopark, Mala...
 
A closer look at tourist information search behavior when travelling abroad: ...
A closer look at tourist information search behavior when travelling abroad: ...A closer look at tourist information search behavior when travelling abroad: ...
A closer look at tourist information search behavior when travelling abroad: ...
 

Similar to Ontology-based Matchmaking to Provide Personalized Offers

Big Data Analytics and Knowledge Discovery through Location-Based Social Netw...
Big Data Analytics and Knowledge Discovery through Location-Based Social Netw...Big Data Analytics and Knowledge Discovery through Location-Based Social Netw...
Big Data Analytics and Knowledge Discovery through Location-Based Social Netw...John Makridis
 
A Review on Tourist Analyzer
A Review on Tourist AnalyzerA Review on Tourist Analyzer
A Review on Tourist AnalyzerIRJET Journal
 
Review of literature(travel and tourism)
Review of literature(travel and tourism)Review of literature(travel and tourism)
Review of literature(travel and tourism)RShrm1
 

Similar to Ontology-based Matchmaking to Provide Personalized Offers (20)

Technology Acceptance of Virtual Reality for Travel Planning
Technology Acceptance of Virtual Reality for Travel PlanningTechnology Acceptance of Virtual Reality for Travel Planning
Technology Acceptance of Virtual Reality for Travel Planning
 
Travellers and Their Joint Characteristics Within the Seven-Factor Model
Travellers and Their Joint Characteristics Within the Seven-Factor ModelTravellers and Their Joint Characteristics Within the Seven-Factor Model
Travellers and Their Joint Characteristics Within the Seven-Factor Model
 
Big Data Analytics and Knowledge Discovery through Location-Based Social Netw...
Big Data Analytics and Knowledge Discovery through Location-Based Social Netw...Big Data Analytics and Knowledge Discovery through Location-Based Social Netw...
Big Data Analytics and Knowledge Discovery through Location-Based Social Netw...
 
Towards a better understanding of the cognitive destination image of the Basq...
Towards a better understanding of the cognitive destination image of the Basq...Towards a better understanding of the cognitive destination image of the Basq...
Towards a better understanding of the cognitive destination image of the Basq...
 
Tourist Analyzer
Tourist AnalyzerTourist Analyzer
Tourist Analyzer
 
Tourism Service Portfolio
Tourism Service PortfolioTourism Service Portfolio
Tourism Service Portfolio
 
Impact of Destination Promotion Videos on Perceived Destination Image and Boo...
Impact of Destination Promotion Videos on Perceived Destination Image and Boo...Impact of Destination Promotion Videos on Perceived Destination Image and Boo...
Impact of Destination Promotion Videos on Perceived Destination Image and Boo...
 
The Role of Personal Value in Information Search Strategies for Community-Bas...
The Role of Personal Value in Information Search Strategies for Community-Bas...The Role of Personal Value in Information Search Strategies for Community-Bas...
The Role of Personal Value in Information Search Strategies for Community-Bas...
 
Personality impacts on the participation in the peer-to-peer (P2P) travel acc...
Personality impacts on the participation in the peer-to-peer (P2P) travel acc...Personality impacts on the participation in the peer-to-peer (P2P) travel acc...
Personality impacts on the participation in the peer-to-peer (P2P) travel acc...
 
Towards Glyph-based Visualizations for Big Data Clustering
Towards Glyph-based Visualizations for Big Data ClusteringTowards Glyph-based Visualizations for Big Data Clustering
Towards Glyph-based Visualizations for Big Data Clustering
 
Automated Assignment of Hotel Descriptions to Travel Behavioural Patterns
 Automated Assignment of Hotel Descriptions to Travel Behavioural Patterns Automated Assignment of Hotel Descriptions to Travel Behavioural Patterns
Automated Assignment of Hotel Descriptions to Travel Behavioural Patterns
 
Automated Assignment of Hotel Descriptions to Travel Behavioural Patterns
Automated Assignment of Hotel Descriptions to Travel Behavioural PatternsAutomated Assignment of Hotel Descriptions to Travel Behavioural Patterns
Automated Assignment of Hotel Descriptions to Travel Behavioural Patterns
 
Big data as input for predicting tourist arrivals
Big data as input for predicting tourist arrivalsBig data as input for predicting tourist arrivals
Big data as input for predicting tourist arrivals
 
An Integrative Model of the Pursuit of Happiness and the Role of Smart Touris...
An Integrative Model of the Pursuit of Happiness and the Role of Smart Touris...An Integrative Model of the Pursuit of Happiness and the Role of Smart Touris...
An Integrative Model of the Pursuit of Happiness and the Role of Smart Touris...
 
A Review on Tourist Analyzer
A Review on Tourist AnalyzerA Review on Tourist Analyzer
A Review on Tourist Analyzer
 
Reframing The Image Of A Destination. A Pre-Post Study On Social Media Exposure
Reframing The Image Of A Destination. A Pre-Post Study On Social Media ExposureReframing The Image Of A Destination. A Pre-Post Study On Social Media Exposure
Reframing The Image Of A Destination. A Pre-Post Study On Social Media Exposure
 
Final defense
Final defenseFinal defense
Final defense
 
Review of literature(travel and tourism)
Review of literature(travel and tourism)Review of literature(travel and tourism)
Review of literature(travel and tourism)
 
Exploiting Web Analytics Tracking for Bootstrapping a Case-based Recommender ...
Exploiting Web Analytics Tracking for Bootstrapping a Case-based Recommender ...Exploiting Web Analytics Tracking for Bootstrapping a Case-based Recommender ...
Exploiting Web Analytics Tracking for Bootstrapping a Case-based Recommender ...
 
Can collaborative use and smart(er) mobile platforms develop better experienc...
Can collaborative use and smart(er) mobile platforms develop better experienc...Can collaborative use and smart(er) mobile platforms develop better experienc...
Can collaborative use and smart(er) mobile platforms develop better experienc...
 

Recently uploaded

Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 3652toLead Limited
 

Recently uploaded (20)

Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
Tech-Forward - Achieving Business Readiness For Copilot in Microsoft 365
 

Ontology-based Matchmaking to Provide Personalized Offers

  • 1. ENTER 2017 Research Track Slide Number 1 Christoph Grün, Julia Neidhardt*), Hannes Werthner E-Commerce Group, TU Wien, Austria *) julia.neidhardt@ec.tuwien.ac.at http://www.ec.tuwien.ac.at Ontology-based Matchmaking to Provide Personalized Offers
  • 2. ENTER 2017 Research Track Slide Number 2 Agenda  Problem Statement  Related Work  Matchmaking Process  Implementation  Evaluation  Conclusion & Future Work → → → → → →
  • 3. ENTER 2017 Research Track Slide Number 3 Problem Statement
  • 4. ENTER 2017 Research Track Slide Number 4 Problem Statement No common view on the tourism space exists  Gap between mental model of tourists and model of tourism offers/space (Gretzel et al.*))  Problem: matching of the customers’ view (tourist’s personality and preferences) with the suppliers’ perspective (tourism objects)  Approach: ontology-based matchmaking process  Focus of this talk: present results of a user study focusing on evaluating the feasibility of the approach *) Gretzel et al. Semantic Representation of Tourism on the Internet. Journal of Travel Research, 2008. → → → → matching
  • 5. ENTER 2017 Research Track Slide Number 5 Related Work
  • 6. ENTER 2017 Research Track Slide Number 6 Recommendation Systems Types of Recommenders Tourist Typologies Semantic Web Ontologies Similarities MTRS Gavalas & Kenteris, 2011 SPETA García-Crespo et al., 2009 Advisor Suite Jananch et al., 2010 etPlanner Höpken et al., 2006 SigTur Moreno et al., 2012 PixMeAway Neidhardt et al., 2014 Demographic- based Burke, 2007 Collaborative- based Herlocker et al., 2004 Content-based Pazzani & Billsus, 2007 Knowledge-based Felfernig et al., 2006 Hybrid Recommenders Schiaffino & Amandi, 2009 Characteristics and motivation of tourists Cohen, 1972 Tourist Roles Yiannakis & Gibson, 1992 Model of a destination’s attractiveness Plog, 2001 Travel career patterns Pearce & Lee, 2005 Tourist Factors Neidhardt et al., 2014 QALL-ME Ou et al., 2008 CRUZAR Mínguez et al., 2010 SPETA García-Crespo et al., 2009 INREDIS Busquet, 2009 HARMONISE Fodor & Werthner, 2005 GETESS Staab et al., 1999 Path-based Rada et al., 1989 Wu & Palmer, 1994 Zhong et al., 2002 Sussna, 1993 Information- based Resnik, 1998 Seco et al., 2004 Feature-based Tversky, 1977 Knappe et al., 2007 Hybrid Jiang & Conrath, 1997 Lian, 1998 Mazuel et al., 2008 Related Work The research draws on knowledge from different fields
  • 7. ENTER 2017 Research Track Slide Number 7 Matchmaking Process
  • 8. ENTER 2017 Research Track Slide Number 8 Matchmaking Process The matchmaking comprises two sub-processes Tourist Types Tourist Tourism Object Generic Preferences Generic Characteristics PROCESS1 PROCESS 1 PROCESS 2
  • 9. ENTER 2017 Research Track Slide Number 9 Matchmaking Process The matchmaking comprises two sub-processes Tourist Types Tourist Tourism Object Generic Preferences Generic Characteristics PROCESS1 MATCHMAKING PROCESS 1 PROCESS 2
  • 10. ENTER 2017 Research Track Slide Number 10 Tourist Matchmaking Process The matchmaking comprises two sub-processes Tourist Types Tourist Tourism Object Generic Preferences Generic Characteristics PROCESS1PROCESS2 Specific Interests Top N Recommendations MATCHMAKING PROCESS 1 PROCESS 2
  • 11. ENTER 2017 Research Track Slide Number 11 Tourist Matchmaking Process The matchmaking comprises two sub-processes Tourist Types Tourist Tourism Object Generic Preferences Generic Characteristics PROCESS1PROCESS2 Specific Interests Top N Recommendations MATCHMAKING PROCESS 1 PROCESS 2
  • 12. ENTER 2017 Research Track Slide Number 12 Tourist Matchmaking Process The matchmaking comprises two sub-processes Tourist Types Tourist Tourism Object Generic Preferences Generic Characteristics PROCESS1PROCESS2 Specific Interests Learn specific interests’dislike churches’ MATCHMAKING PROCESS 1 PROCESS 2 Specific Interests
  • 13. ENTER 2017 Research Track Slide Number 13 Tourist Matchmaking Process The matchmaking comprises two sub-processes Tourist Types Tourist Tourism Object Generic Preferences Generic Characteristics PROCESS1PROCESS2 Tourism Object Specific Attributes Learn specific interests’dislike churches’ MATCHMAKING PROCESS 1 PROCESS 2 Specific Interests
  • 14. ENTER 2017 Research Track Slide Number 14 Matchmaking Process The matchmaking comprises two sub-processes Tourist Types Tourist Tourism Object Generic Preferences Generic Characteristics PROCESS1PROCESS2 Tourist Tourism Object Specific Interests Specific Attributes Learn specific interests’dislike churches’ MATCHMAKING MATCHMAKING Tourism Ontology PROCESS 1 PROCESS 2
  • 15. ENTER 2017 Research Track Slide Number 15  Fragment of the cDOTT*) ontology depicting the semantic description of the Viennese attraction Schönbrunn Palace Matchmaking Process A tourism ontology is used to drive the matchmaking → PROCESS 1 PROCESS 2 *) cDOTT = core Domain Ontology of Travel and Tourism Barta et al. Covering the semantic space of tourism: An approach based on modularized ontologies. In Proceedings of the 1st Workshop on Context, Information and Ontologies, 2009.
  • 16. ENTER 2017 Research Track Slide Number 16  Tourist types are a valid means to predict the set of activities in which tourist like to engage*).  We use the 7 tourist factors (e.g. culture loving) presented by Neidhardt et al.**)  Predefined tourist factors can be used as stereotypical approach to generate a generic profile  Orthogonal vectors are suited to model tourist factors Tourist Generic Preferences First Matchmaking Process Generating a high-level tourist profile Tourist Types *) Gretzel et al. Tell me who you are and I will tell you where to go: Use of Travel Personalities in Destination Recommendation Systems. Information Technology & Tourism, 7:3– 12, 2004. **) Neidhardt et al. A picture-based approach to recommender systems. Information Technology & Tourism, 15(1), 2014. → PROCESS 1 PROCESS 2 → → → Sight Seeker Cultural Visitor Nature Lover Avid AthletheAction Seeker Educational Buff Sun Worshipper PROCESS1
  • 17. ENTER 2017 Research Track Slide Number 17 Tourist Second Matchmaking Process Exploit ratings to learn specific interests of tourist Tourist TypesPROCESS2 Specific Interests Learn specific interests Specific Interests ’dislike churches’ PROCESS 1 PROCESS 2 Tourist Tourism Object PROCESS1 MATCHMAKING Sight Seeker Cultural Visitor Nature Lover Avid AthletheAction Seeker Educational Buff Sun Worshipper Sight Seeker Cultural Visitor Nature Lover Avid AthletheAction Seeker Educational Buff Sun Worshipper
  • 18. ENTER 2017 Research Track Slide Number 18 Tourist Second Matchmaking Process Exploit ratings to learn specific interests of tourist Tourist TypesPROCESS2 Specific Interests Learn specific interests Tourism Object Specific Interests Specific Attributes ’dislike churches’ PROCESS 1 PROCESS 2 Tourist Tourism Object PROCESS1 MATCHMAKING Sight Seeker Cultural Visitor Nature Lover Avid AthletheAction Seeker Educational Buff Sun Worshipper Sight Seeker Cultural Visitor Nature Lover Avid AthletheAction Seeker Educational Buff Sun Worshipper
  • 19. ENTER 2017 Research Track Slide Number 19 Tourist Second Matchmaking Process Exploit ratings to learn specific interests of tourist Tourist TypesPROCESS2 Specific Interests Learn specific interests Tourism Object Specific Interests Specific Attributes Tourism Ontology ’dislike churches’ PROCESS 1 PROCESS 2 Tourist Tourism Object PROCESS1 MATCHMAKING Sight Seeker Cultural Visitor Nature Lover Avid AthletheAction Seeker Educational Buff Sun Worshipper Sight Seeker Cultural Visitor Nature Lover Avid AthletheAction Seeker Educational Buff Sun Worshipper
  • 20. ENTER 2017 Research Track Slide Number 20  Ratings of objects are used to learn the tourist’s specific interests  The specific interests are represented as an overlay of the ontological model Second Matchmaking Process Using an ontology-based approach to model the profile Tourist Specific Interests → → PROCESS 1 PROCESS 2 PROCESS2 Imperial Furniture Collection Identify leaf concepts that describe object Assign numerical score to the leaf concepts Exploit ontological hierarchy to infer interest score for super-concepts (spreading activation) using a propagation function following Sieg et al., 2007. 1 2 3 Sieg et al. Web search personalization with ontological user profiles. In CIKM ’07: Proceedings of the sixteenth ACM conference on Conference on information and knowledge management, 2007. Ontology Concept( Concept(Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept(Concept(Concept(Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept( Concept(Concept(
  • 21. ENTER 2017 Research Track Slide Number 21 Implementation
  • 22. ENTER 2017 Research Track Slide Number 22 Prototype for the City of Vienna
  • 23. ENTER 2017 Research Track Slide Number 23 Recommended tourism objects
  • 24. ENTER 2017 Research Track Slide Number 24 Detailed description of a tourism object
  • 25. ENTER 2017 Research Track Slide Number 25 Evaluation
  • 26. ENTER 2017 Research Track Slide Number 26 Evaluation 54 users completed the questionnaire  Period of 3 months from June to September 2015  Target group  Tourists who visited or plan to visit Vienna in near future  Persons who know this city well (live or work here)  User sessions identified from Weblog information  70 users started to fill out questionnaire  54 users completed the questionnaire → final dataset Age distribution of users within final dataset (n=54) → → →
  • 27. ENTER 2017 Research Track Slide Number 27 Evaluation Users identify themselves with a mixture of factors  Participants identify themselves with a mixture of all 7 factors  about 75% chose at least 5 factors → users tend to select more than 1 tourist factor if they have the choice  The factors Sight Seeker, Cultural Visitor and Nature Lover were most often selected → Vienna is a city destination 1 1 Number of factors selected by the users (n=54) Distribution of the tourist factors on average (n=54) 2 2 →
  • 28. ENTER 2017 Research Track Slide Number 28 Evaluation 50% of the users executed 1-3 recommendation cycles  This figure shows the number of recommendation cycles  About 70% of the users explored the recommendations proposed by the system within 1 to 6 recommendation cycles  The median has the value 3 → 50% of the users executed 1-3 cycles 1 2 1 2 → (n=54)
  • 29. ENTER 2017 Research Track Slide Number 29 Evaluation  About 75% of the objects were added in the first 3 cycles to the favourites  On average, 8.5 ratings had been given in each user session (ca. 5.3 positive and 3.2 negative ratings), 40% ratings were stated in the 1 cycle → →
  • 30. ENTER 2017 Research Track Slide Number 30 Evaluation Measuring the relevance of the recommendations  As in our case no dataset is available, we decided to  show the users 10 objects that were randomly chosen from the whole dataset and had not been recommended before  let them decide if one or more objects are relevant for them (by adding them to the top-N list) About 70 % of the users added at maximum 1 of the randomly shown object to their favorites → Feedback from the users to the randomly shown objects, n=54 this might be an indication that they were quite satisfied with the recommendations Why had these objects not been recommended before? • Object is related to a tourist factor not selected by the user • Other objects of same category already recommended • Objects of other categories positively rated → user profile more aligned with profiles of those objects 1 2 →
  • 31. ENTER 2017 Research Track Slide Number 31 Evaluation Participants’ feedback  Information collected from the questionnaire→
  • 32. ENTER 2017 Research Track Slide Number 32 Conclusion & Future Work
  • 33. ENTER 2017 Research Track Slide Number 33 Conclusion & Future Work  The goal was to close the gap between users’ needs and suppliers’ perspective by developing a matchmaking process  A Web-based prototype was implemented for the city Vienna  A first evaluation was conducted which aimed to investigate the feasibility of the approach  Overall, the evaluation shows that the two-step matchmaking process and the feedback cycle work  In future we will define automated procedures to annotate the tourism objects semantically → → → → →
  • 35. ENTER 2017 Research Track Slide Number 35 Appendix
  • 36. ENTER 2017 Research Track Slide Number 36 Evaluation Correlation between the tourist factors
  • 37. ENTER 2017 Research Track Slide Number 37 With score propagation Evaluation Score propagation improves recommendations  Propagation of user interests within the semantic model affects the position of relevant tourism objects in the Top-N list Without score propagation 3 • Objects might be relevant but not included in Top-N list3 ghotic/romanesque architecturestyle 2 • On the next positions are 4 churches as they belong to the «ghotic/architeture» style as «St. Stephen‘s Cathedral» 2 Positive Rating of St. Stephen’s Cathedral • Positive rating «St. Stephen‘s Cathedral»1 1 • Objects are now directly placed on subsequent positions within the list. Due to score propagation in the semantic model, the user profile gets more similar to the profiles of the objects (larger overlap) 2 2 Positive Rating of St. Stephen’s Cathedral • Positive rating «St. Stephen‘s Cathedral» → first position 1 1 →