SlideShare une entreprise Scribd logo
1  sur  35
Télécharger pour lire hors ligne
Explainable Recommendations
Opinionated Explanations in Recommender Systems.
Barry Smyth, Aonghus Lawlor, Khalil Muhammad,

and Ruihai Dong
2
Overview
The Ubiquity of Recommendations
Reviews, Opinions, Recommendations
From Recommendations to Explanations
4
Recommendation
Explanation
Sources of Recommendation Knowledge
Transactional & Behavioural Data

Clicks, purchases, likes, rating, actions (save to wish-list)

Content & Meta Data

Features and tags, structured and unstructured.

Experiential Data

User-generated opinions. Based on real subjective experiences vs
objective catalog metadata.

5
6
7
What about all of
these reviews?
Plentiful
Experiential
Influential
8
... focus on extracting only features and sentiment from a collection
of reviews for product ...

(e, f, s, h, t)


... to produce aggregate product descriptions from e1,..,en.
The Anatomy of an Opinion
Aspect-based Opinion Mining
10
DSLR: ++
Value: ++
Build Quality: -
Weight: +
Grip: +
Image Quality: +
Resolution: -
Price: +
Battery Life: ---
11
The Fuji X100 is a great camera. It looks beautiful and takes great quality images.
I have found the battery life to be superb during normal use. I only seem to charge
after well over 1000 shots. The build quality is excellent and it is a joy to hold.
The camera is not without its quirks however and it does take some getting used to.
The auto focus can be slow to catch, for example. So it's not so good for action shots
but it does take great portraits and its night shooting is excellent.
Product Reviews
Feature Extraction Sentiment Mining
Generate Cases
R1, …, Rk
(F1,S1)…(Fn,Sn)
ANs & NNs Ns
Bi-Gram Analysis Unigram Analysis
Validation & Filtering
IdentifySentimentWords
ExtractOpinionPatterns
SentimentAssignment
(F1,S1,wmin1)…
(F1,S1,S2,...)…
FilterFeatures
Summarise
Sentiment
(F1,L1,L2,...)…
(F1,Sent1)…
(Dong et al, ICCBR 2013)
Aspect-based Opinion Mining
12
DSLR: ++
Value: ++
Build Quality: -
Weight: +
Grip: +
Image Quality: +
Resolution: -
Price: +
Battery Life: ---
From Reviews to Explanations
13
14
Opinionated Explanations
Opinionated Explanation Interfaces

Incorporating explanations into recommendation interfaces.

From Basic to Compelling Explanations

Filtering and specialising explanations.

Explanation-Based Ranking

Using explanation strength to rank recommendations.
15
Explanation Interface
Per Item Explanations

Feature-Based

Sentiment Oriented

Reference Sets
16
17
Hotel/Item Descriptions
Hotel, hi, is associated with a set of reviews, R(hi) = {r1,…,rn}.
Opinion mining process extracts f1,…fm for hi from R(hi).
18
Item Descriptions
Each feature has an importance score (imp) and a sentiment
score (s)…

Note: pos(fj,hi) = num. of mentions of fj in hi labeled as +’ve.
19
A Basic Explanation for hi
20
Computing BT/WT Scores
21
From Basic to Compelling Explanations
Not all of the features in an explanation make for strong
reasons to select or reject a hotel.

In previous example, “Free Breakfast” is a pro but it is only
better than 10% of the alternatives. 

We can use better/worse scores to help identify compelling
features and filter out weaker, less compelling features.
22
Compelling Explanations
23
Personalised Compelling Explanations
24
Explanation-Based Ranking
25
But the link between
recommendations and explanations 

remains tenuous …
26
Explanation-Based Ranking
But what if explanations played a more intimate role in
recommendation / ranking?
The idea is to rank recommendations based on the
strength of their corresponding explanation.
In other words, a recommendation should be preferred if it
can be explained in a compelling way to the user.
Explanation Strength
28
Does it Work?
29
Evaluation
5,179 TripAdvisor users each with at least 4 reviews; 224,760 hotel
reviews for 2,298 hotels.
For each uT, and hB, reviewed (booked) hotel, plus top TA
alternatives
Generate explanations for each of the 10 “recommended” hotels and
rank by explanation strength.
uT : {hB, h1, …, h9}
Baseline Comparisons
As a baseline we can also rank the recommended hotels
based on TA’s average review ratings.
Compare the number of pros/cons in explanations based
on rank of recommendations; higher rank = more pros /
fewer cons.
Compare position of booked hotel in baseline-ranking vs.
explanation-ranked recommendations.
Ranked by Compelling Explanation Strength
Ranked by TA Rating
33
Results Summary
Recommendations ranked by explanation strength
prioritises better hotels (more pros and fewer cons).
Ranking by TA review score produces less compelling
recommendations.
On average the booked hotel occurred at rank position 5
→ not necessarily best choice for the user at the time?
Conclusions
User reviews can be a rich source of recommendation
knowledge.
Novel approach to explanation based on features mined
from user-generated reviews.
Creating personalised and compelling explanations.
Using explanations to guide recommendation ranking.

Contenu connexe

Similaire à Explainable recommendations - IJCAI 2017 XAI Workshop

Brand Mind Territory
Brand Mind TerritoryBrand Mind Territory
Brand Mind Territorydoron_bs
 
Entirely tailored sentiment analysis - MeaningCloud webinar
Entirely tailored sentiment analysis - MeaningCloud webinarEntirely tailored sentiment analysis - MeaningCloud webinar
Entirely tailored sentiment analysis - MeaningCloud webinarMeaningCloud
 
Week 06Conjoint Analysishttpswww.smh.com.au.docx
Week 06Conjoint Analysishttpswww.smh.com.au.docxWeek 06Conjoint Analysishttpswww.smh.com.au.docx
Week 06Conjoint Analysishttpswww.smh.com.au.docxjessiehampson
 
Tips on ASO & Ad Monetization - Fiona Shih | Animoca Brands
Tips on ASO & Ad Monetization - Fiona Shih | Animoca BrandsTips on ASO & Ad Monetization - Fiona Shih | Animoca Brands
Tips on ASO & Ad Monetization - Fiona Shih | Animoca BrandsFiona Yu-Chun Shih
 
Lexden's 'what matters most' in customer experience
Lexden's 'what matters most' in customer experienceLexden's 'what matters most' in customer experience
Lexden's 'what matters most' in customer experienceChristopher Brooks
 
Combining the opinion profile modeling with complex context filtering for Con...
Combining the opinion profile modeling with complex context filtering for Con...Combining the opinion profile modeling with complex context filtering for Con...
Combining the opinion profile modeling with complex context filtering for Con...Twitter Inc.
 
IRJET- Implementation of Review Selection using Deep Learning
IRJET-  	  Implementation of Review Selection using Deep LearningIRJET-  	  Implementation of Review Selection using Deep Learning
IRJET- Implementation of Review Selection using Deep LearningIRJET Journal
 

Similaire à Explainable recommendations - IJCAI 2017 XAI Workshop (7)

Brand Mind Territory
Brand Mind TerritoryBrand Mind Territory
Brand Mind Territory
 
Entirely tailored sentiment analysis - MeaningCloud webinar
Entirely tailored sentiment analysis - MeaningCloud webinarEntirely tailored sentiment analysis - MeaningCloud webinar
Entirely tailored sentiment analysis - MeaningCloud webinar
 
Week 06Conjoint Analysishttpswww.smh.com.au.docx
Week 06Conjoint Analysishttpswww.smh.com.au.docxWeek 06Conjoint Analysishttpswww.smh.com.au.docx
Week 06Conjoint Analysishttpswww.smh.com.au.docx
 
Tips on ASO & Ad Monetization - Fiona Shih | Animoca Brands
Tips on ASO & Ad Monetization - Fiona Shih | Animoca BrandsTips on ASO & Ad Monetization - Fiona Shih | Animoca Brands
Tips on ASO & Ad Monetization - Fiona Shih | Animoca Brands
 
Lexden's 'what matters most' in customer experience
Lexden's 'what matters most' in customer experienceLexden's 'what matters most' in customer experience
Lexden's 'what matters most' in customer experience
 
Combining the opinion profile modeling with complex context filtering for Con...
Combining the opinion profile modeling with complex context filtering for Con...Combining the opinion profile modeling with complex context filtering for Con...
Combining the opinion profile modeling with complex context filtering for Con...
 
IRJET- Implementation of Review Selection using Deep Learning
IRJET-  	  Implementation of Review Selection using Deep LearningIRJET-  	  Implementation of Review Selection using Deep Learning
IRJET- Implementation of Review Selection using Deep Learning
 

Dernier

RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.natarajan8993
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样vhwb25kk
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]📊 Markus Baersch
 
Heart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectHeart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectBoston Institute of Analytics
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptSonatrach
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝soniya singh
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Colleen Farrelly
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...limedy534
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Sapana Sha
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queensdataanalyticsqueen03
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Jack DiGiovanna
 
Identifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanIdentifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanMYRABACSAFRA2
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhijennyeacort
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024thyngster
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 

Dernier (20)

RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
 
GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]GA4 Without Cookies [Measure Camp AMS]
GA4 Without Cookies [Measure Camp AMS]
 
Heart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis ProjectHeart Disease Classification Report: A Data Analysis Project
Heart Disease Classification Report: A Data Analysis Project
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
 
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
Call Girls in Defence Colony Delhi 💯Call Us 🔝8264348440🔝
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 
Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024Generative AI for Social Good at Open Data Science East 2024
Generative AI for Social Good at Open Data Science East 2024
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
Effects of Smartphone Addiction on the Academic Performances of Grades 9 to 1...
 
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
Saket, (-DELHI )+91-9654467111-(=)CHEAP Call Girls in Escorts Service Saket C...
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
E-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptxE-Commerce Order PredictionShraddha Kamble.pptx
E-Commerce Order PredictionShraddha Kamble.pptx
 
Top 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In QueensTop 5 Best Data Analytics Courses In Queens
Top 5 Best Data Analytics Courses In Queens
 
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
Building on a FAIRly Strong Foundation to Connect Academic Research to Transl...
 
Identifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population MeanIdentifying Appropriate Test Statistics Involving Population Mean
Identifying Appropriate Test Statistics Involving Population Mean
 
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝DelhiRS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
RS 9000 Call In girls Dwarka Mor (DELHI)⇛9711147426🔝Delhi
 
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
Consent & Privacy Signals on Google *Pixels* - MeasureCamp Amsterdam 2024
 
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 

Explainable recommendations - IJCAI 2017 XAI Workshop

  • 1. Explainable Recommendations Opinionated Explanations in Recommender Systems. Barry Smyth, Aonghus Lawlor, Khalil Muhammad, and Ruihai Dong
  • 2. 2
  • 3. Overview The Ubiquity of Recommendations Reviews, Opinions, Recommendations From Recommendations to Explanations
  • 5. Sources of Recommendation Knowledge Transactional & Behavioural Data Clicks, purchases, likes, rating, actions (save to wish-list) Content & Meta Data Features and tags, structured and unstructured. Experiential Data User-generated opinions. Based on real subjective experiences vs objective catalog metadata. 5
  • 6. 6
  • 7. 7 What about all of these reviews?
  • 9. ... focus on extracting only features and sentiment from a collection of reviews for product ...
 (e, f, s, h, t) 
 ... to produce aggregate product descriptions from e1,..,en. The Anatomy of an Opinion
  • 10. Aspect-based Opinion Mining 10 DSLR: ++ Value: ++ Build Quality: - Weight: + Grip: + Image Quality: + Resolution: - Price: + Battery Life: ---
  • 11. 11 The Fuji X100 is a great camera. It looks beautiful and takes great quality images. I have found the battery life to be superb during normal use. I only seem to charge after well over 1000 shots. The build quality is excellent and it is a joy to hold. The camera is not without its quirks however and it does take some getting used to. The auto focus can be slow to catch, for example. So it's not so good for action shots but it does take great portraits and its night shooting is excellent. Product Reviews Feature Extraction Sentiment Mining Generate Cases R1, …, Rk (F1,S1)…(Fn,Sn) ANs & NNs Ns Bi-Gram Analysis Unigram Analysis Validation & Filtering IdentifySentimentWords ExtractOpinionPatterns SentimentAssignment (F1,S1,wmin1)… (F1,S1,S2,...)… FilterFeatures Summarise Sentiment (F1,L1,L2,...)… (F1,Sent1)… (Dong et al, ICCBR 2013)
  • 12. Aspect-based Opinion Mining 12 DSLR: ++ Value: ++ Build Quality: - Weight: + Grip: + Image Quality: + Resolution: - Price: + Battery Life: ---
  • 13. From Reviews to Explanations 13
  • 14. 14
  • 15. Opinionated Explanations Opinionated Explanation Interfaces Incorporating explanations into recommendation interfaces. From Basic to Compelling Explanations Filtering and specialising explanations. Explanation-Based Ranking Using explanation strength to rank recommendations. 15
  • 16. Explanation Interface Per Item Explanations Feature-Based Sentiment Oriented Reference Sets 16
  • 17. 17
  • 18. Hotel/Item Descriptions Hotel, hi, is associated with a set of reviews, R(hi) = {r1,…,rn}. Opinion mining process extracts f1,…fm for hi from R(hi). 18
  • 19. Item Descriptions Each feature has an importance score (imp) and a sentiment score (s)… Note: pos(fj,hi) = num. of mentions of fj in hi labeled as +’ve. 19
  • 20. A Basic Explanation for hi 20
  • 22. From Basic to Compelling Explanations Not all of the features in an explanation make for strong reasons to select or reject a hotel. In previous example, “Free Breakfast” is a pro but it is only better than 10% of the alternatives. We can use better/worse scores to help identify compelling features and filter out weaker, less compelling features. 22
  • 26. But the link between recommendations and explanations 
 remains tenuous … 26
  • 27. Explanation-Based Ranking But what if explanations played a more intimate role in recommendation / ranking? The idea is to rank recommendations based on the strength of their corresponding explanation. In other words, a recommendation should be preferred if it can be explained in a compelling way to the user.
  • 30. Evaluation 5,179 TripAdvisor users each with at least 4 reviews; 224,760 hotel reviews for 2,298 hotels. For each uT, and hB, reviewed (booked) hotel, plus top TA alternatives Generate explanations for each of the 10 “recommended” hotels and rank by explanation strength. uT : {hB, h1, …, h9}
  • 31. Baseline Comparisons As a baseline we can also rank the recommended hotels based on TA’s average review ratings. Compare the number of pros/cons in explanations based on rank of recommendations; higher rank = more pros / fewer cons. Compare position of booked hotel in baseline-ranking vs. explanation-ranked recommendations.
  • 32. Ranked by Compelling Explanation Strength
  • 33. Ranked by TA Rating 33
  • 34. Results Summary Recommendations ranked by explanation strength prioritises better hotels (more pros and fewer cons). Ranking by TA review score produces less compelling recommendations. On average the booked hotel occurred at rank position 5 → not necessarily best choice for the user at the time?
  • 35. Conclusions User reviews can be a rich source of recommendation knowledge. Novel approach to explanation based on features mined from user-generated reviews. Creating personalised and compelling explanations. Using explanations to guide recommendation ranking.