SlideShare une entreprise Scribd logo
Ganesan & Zhai 2012, Information Retrieval, Vol 15, Number 2




Kavita Ganesan (www.kavita-ganesan.com)
University of Illinois @ Urbana Champaign
Journal
Project Page
   Currently: No easy or direct way of finding
    entities (e.g. products, people, businesses)
    based on online opinions

   You need to read opinions about different
    entities to find entities that fulfill personal
    criteria
    e.g. finding mp3 players with ‘good sound quality’
   Currently: No easy or direct way of finding
    entities (e.g. products, people, businesses)
    based on online opinions

   You need to read opinions about different
    entities to find entities that fulfill personal
    criteria
     (e.g. finding mp3 players with ‘good sound quality’
       Time consuming process & impairs
                  user productivity!
   Use existing opinions to rank entities based on
    a set of unstructured user preferences

   Example of user preferences:
     Finding a hotel: “clean rooms, heated pools”
     Finding a restaurant: “authentic food, good ambience”
   Most obvious way: use results of existing
    opinion mining methods
     Find sentiment ratings on various aspects
      ▪ For example, for an mp3 player: find ratings for screen, sound,
        battery life aspects
      ▪ Then, rank entities based on these discovered aspect ratings
     Problem is that this is Not practical!
      ▪ Costly – It is costly to mine large amounts of textual content
      ▪ Prior knowledge – You need to know the set of queriable
        aspects in advance. So, you may have to define aspects for
        each domain either manually or through text mining
      ▪ Supervision – Most of the existing methods rely on some form
        of supervision like the presence of overall user ratings. Such
        information may not always be available.
   Leverage Existing Text Retrieval Models
   Why?
     Retrieval models can scale up to large amounts of
      textual content
     The models themselves can be tweaked or
      redefined
     This does not require costly information extraction
      or text mining
Leveraging robust text retrieval models
             Indexed
                        rank
 Entity 1    Entity 1
             Reviews

                        rank      retrieval         User Preferences
             Entity 2              models               (query)
 Entity 2
             Reviews             (BM25, LM, PL2)
                        rank

 Entity 3    Entity 3
             Reviews             Keyword match
                               between user prefs
                                & textual reviews
Leveraging robust text retrieval models
             Indexed
                        rank
 Entity 3    Entity 3
             Reviews

                        rank      retrieval         User Preferences
             Entity 2              models               (query)
 Entity 2
             Reviews             (BM25, LM, PL2)
                        rank

 Entity 1    Entity 1
             Reviews             Keyword match
                               between user prefs
                                & textual reviews
   Based on the basic setup, this ranking problem seems
    similar to regular document retrieval problem
   However, there are important differences:
1. The query is meant to express a user's preferences in keywords
    Query is expected to be longer than regular keyword queries
    Query may contain sub-queries expressing preferences for different
     aspects
    It may actually be beneficial to model these semantic aspects

2. Ranking is to capture how well an entity satisfies a user's
   preferences
    Not the relevance of a document to a query (as in regular retrieval)
    The matching of opinion/sentiment words would be important in
     this case
   Investigate use of text retrieval models for the
    task of Opinion-Based Entity Ranking

   Explore some extensions over IR models

   Propose evaluation method for the ranking task

   User Study
     To determine if results make sense to users
     Validate effectiveness of evaluation method
   In standard text retrieval we cannot distinguish
    the multiple preferences in a query.
    For example: “clean rooms, cheap, good service”
     Would be treated as a long keyword query even
      though there are 3 preferences in the query
     Problem with this is that an entity may score highly
      because of matching one aspect extremely well

   To improve this:
     We try to score each preference separately and then
      combine the results
Aspect Queries

“clean rooms, cheap,                                             “good
                       “clean rooms”        “cheap”
                                                                service”
    good service”

                                                                     scored
                                    retrieval model                separately
   retrieval model

                             result set 1   result set 2   result set 3
       Results

                                                              results
                                            Results
                                                             combined
   In standard retrieval models the matching of
    an opinion word & a standard topic word is
    not distinguished

   However, with Opinion-Based Entity Ranking:
     It is important to match opinion words in the
      query, but opinion words tend to have more
      variation than topic words
     Solution: Expand a query with similar opinion
      words to help emphasize the matching of opinions
Similar Meaning to
Fantastic battery life   “Fantastic battery life”
      Query
                            Good battery life


                            Great battery life


                           Excellent battery life

                           Review documents
Similar Meaning to
Fantastic battery life          “Fantastic battery life”
      Query
             Add synonyms of
                                   Good battery life
             word “fantastic”


  Fantastic, good,                 Great battery life
  great,excellent…
     battery life
                                  Excellent battery life
  Expanded Query
                                  Review documents
   Document Collection

   Gold Standard: Relevance Judgement

   User Queries

   Evaluation Measure
   Document Collection:
     Reviews of Hotels – Tripadvisor
     Reviews of Cars – Edmunds



                       Numerical
                     aspect ratings
                                          Gold
                                        standard
         Free text reviews
   Gold Standard:
     Needed to asses performance of ranking task


   For each entity & for each aspect (in dataset):
     Average numerical ratings across reviews. This will
      give the judgment score for each aspect
     Assumption:
      Since the numerical ratings were given by users,
      this would be a good approximation to actual
      human judgment
   Gold Standard:
    Ex. User looking for cars with “good performance”
     Ideally, the system should return cars with
      ▪ High numerical ratings on performance aspect
      ▪ Otherwise, we can say that the system is not doing well in
        ranking
         Should have high
         ratings on
         performance
   User Queries
     Semi synthethic queries
     Not able to obtain natural sample of queries

     Ask users to specify preferences on different aspects
      of car & hotel based on aspects available in dataset
      ▪ Seed queries
      ▪ Ex. Fuel: “good gas mileage”, “great mpg”

     Randomly combine seed queries from different
      aspects  forms synthetic queries
      ▪ Ex. Query 1: “great mpg, reliable car”
      ▪ Ex. Query 2: “comfortable, good performance”
   Evaluation Measure: nDCG
     This measure is ideal because it is based on
      multiple levels of ranking
     The numerical ratings used as judgment scores has
      a range of values and nDCG will actually support
      this.
   Users were asked to manually determine the relevance
    of system generated rankings to a set of queries

Two reasons for user study:
 Validate that results made sense to real users
     On average, users thought that the entities retrieved by the
      system were a reasonable match to the queries

   Validate effectiveness of gold standard rankings
     Gold standard ranking has relatively strong agreement
      with user rankings. This means the gold standard based on
      numerical ratings is a good approximation to human
      judgment
Most effective          Most effective
                               on BM25 (p23)           on BM25 (p23)
8.0%         Hotels               2.5%                Cars
6.0%                              2.0%
                                  1.5%
4.0%
                                  1.0%
2.0%                              0.5%
0.0%                              0.0%
       PL2      LM      BM25                    PL2      LM       BM25
       QAM   QAM + OpinExp                 QAM        QAM + OpinExp


Improvement in ranking using QAM
Improvement in ranking using QAM + OpinExp
   Lightweight approach to ranking entities based
    on opinions
     Use existing text retrieval models

   Explored some enhancements over retrieval
    models
     Namely opinion expansion & query aspect modeling
     Both showed some improvement in ranking

   Proposed evaluation method using user ratings
     User study shows that the evaluation method is sound
     This method can be used for future evaluation tasks

Contenu connexe

Tendances

VB.NET untuk .NET Programmer
VB.NET untuk .NET ProgrammerVB.NET untuk .NET Programmer
VB.NET untuk .NET Programmer
Nurdin Al-Azies
 
Inverse Matrix & Determinants
Inverse Matrix & DeterminantsInverse Matrix & Determinants
Inverse Matrix & Determinants
itutor
 
_200_bai_luong_giac_co_loi_giai_chi_tiet
_200_bai_luong_giac_co_loi_giai_chi_tiet_200_bai_luong_giac_co_loi_giai_chi_tiet
_200_bai_luong_giac_co_loi_giai_chi_tiet
Vân Đào
 
Lec 17 heap data structure
Lec 17 heap data structureLec 17 heap data structure
Lec 17 heap data structure
Sajid Marwat
 

Tendances (20)

Data structures using c
Data structures using cData structures using c
Data structures using c
 
BCA DATA STRUCTURES LINEAR ARRAYS MRS.SOWMYA JYOTHI
BCA DATA STRUCTURES LINEAR ARRAYS MRS.SOWMYA JYOTHIBCA DATA STRUCTURES LINEAR ARRAYS MRS.SOWMYA JYOTHI
BCA DATA STRUCTURES LINEAR ARRAYS MRS.SOWMYA JYOTHI
 
CS8391 Data Structures Part B Questions Anna University
CS8391 Data Structures Part B Questions Anna UniversityCS8391 Data Structures Part B Questions Anna University
CS8391 Data Structures Part B Questions Anna University
 
Heaps & priority queues
Heaps & priority queuesHeaps & priority queues
Heaps & priority queues
 
Linear Equations
Linear EquationsLinear Equations
Linear Equations
 
VB.NET untuk .NET Programmer
VB.NET untuk .NET ProgrammerVB.NET untuk .NET Programmer
VB.NET untuk .NET Programmer
 
8. Graph - Data Structures using C++ by Varsha Patil
8. Graph - Data Structures using C++ by Varsha Patil8. Graph - Data Structures using C++ by Varsha Patil
8. Graph - Data Structures using C++ by Varsha Patil
 
Inverse Matrix & Determinants
Inverse Matrix & DeterminantsInverse Matrix & Determinants
Inverse Matrix & Determinants
 
Daiso11 chuong-2a (3)
Daiso11 chuong-2a (3)Daiso11 chuong-2a (3)
Daiso11 chuong-2a (3)
 
My Lecture Notes from Linear Algebra
My Lecture Notes fromLinear AlgebraMy Lecture Notes fromLinear Algebra
My Lecture Notes from Linear Algebra
 
Matlab on basic mathematics
Matlab on basic mathematicsMatlab on basic mathematics
Matlab on basic mathematics
 
Hoán vị, chỉnh hợp, tổ hợp
Hoán vị, chỉnh hợp, tổ hợpHoán vị, chỉnh hợp, tổ hợp
Hoán vị, chỉnh hợp, tổ hợp
 
Hash table
Hash tableHash table
Hash table
 
Data Structure and Algorithms The Tower of Hanoi
Data Structure and Algorithms The Tower of HanoiData Structure and Algorithms The Tower of Hanoi
Data Structure and Algorithms The Tower of Hanoi
 
Hash table in data structure and algorithm
Hash table in data structure and algorithmHash table in data structure and algorithm
Hash table in data structure and algorithm
 
De thi hsg toan 8
De thi hsg toan 8 De thi hsg toan 8
De thi hsg toan 8
 
_200_bai_luong_giac_co_loi_giai_chi_tiet
_200_bai_luong_giac_co_loi_giai_chi_tiet_200_bai_luong_giac_co_loi_giai_chi_tiet
_200_bai_luong_giac_co_loi_giai_chi_tiet
 
Array ADT(Abstract Data Type)|Data Structure
Array ADT(Abstract Data Type)|Data StructureArray ADT(Abstract Data Type)|Data Structure
Array ADT(Abstract Data Type)|Data Structure
 
Sorting Algorithms
Sorting AlgorithmsSorting Algorithms
Sorting Algorithms
 
Lec 17 heap data structure
Lec 17 heap data structureLec 17 heap data structure
Lec 17 heap data structure
 

En vedette

Query based summarization
Query based summarizationQuery based summarization
Query based summarization
damom77
 
CVML2011: human action recognition (Ivan Laptev)
CVML2011: human action recognition (Ivan Laptev)CVML2011: human action recognition (Ivan Laptev)
CVML2011: human action recognition (Ivan Laptev)
zukun
 
Listening exercise ted 2
Listening exercise ted 2Listening exercise ted 2
Listening exercise ted 2
Nini Paz
 
Blubag brochure
Blubag brochureBlubag brochure
Blubag brochure
fooserv
 
Listening exercise ted 2
Listening exercise ted 2Listening exercise ted 2
Listening exercise ted 2
Nini Paz
 
Interactive tv fri123 7
Interactive tv fri123 7Interactive tv fri123 7
Interactive tv fri123 7
설란 문
 
Supermarket
SupermarketSupermarket
Supermarket
Nini Paz
 

En vedette (20)

Opinosis Presentation @ Coling 2010: Opinosis - A Graph Based Approach to Abs...
Opinosis Presentation @ Coling 2010: Opinosis - A Graph Based Approach to Abs...Opinosis Presentation @ Coling 2010: Opinosis - A Graph Based Approach to Abs...
Opinosis Presentation @ Coling 2010: Opinosis - A Graph Based Approach to Abs...
 
Opinion Mining Tutorial (Sentiment Analysis)
Opinion Mining Tutorial (Sentiment Analysis)Opinion Mining Tutorial (Sentiment Analysis)
Opinion Mining Tutorial (Sentiment Analysis)
 
Query based summarization
Query based summarizationQuery based summarization
Query based summarization
 
Micropinion Generation
Micropinion GenerationMicropinion Generation
Micropinion Generation
 
Introduction to Java Strings, By Kavita Ganesan
Introduction to Java Strings, By Kavita GanesanIntroduction to Java Strings, By Kavita Ganesan
Introduction to Java Strings, By Kavita Ganesan
 
Context based sentiment analysis
Context based sentiment analysisContext based sentiment analysis
Context based sentiment analysis
 
ACIS 2015 Bibliographical-based Facets for Expertise Search
ACIS 2015 Bibliographical-based Facets for Expertise SearchACIS 2015 Bibliographical-based Facets for Expertise Search
ACIS 2015 Bibliographical-based Facets for Expertise Search
 
CVML2011: human action recognition (Ivan Laptev)
CVML2011: human action recognition (Ivan Laptev)CVML2011: human action recognition (Ivan Laptev)
CVML2011: human action recognition (Ivan Laptev)
 
Aspect Mining Techniques
Aspect Mining TechniquesAspect Mining Techniques
Aspect Mining Techniques
 
Clothes
ClothesClothes
Clothes
 
Listening exercise ted 2
Listening exercise ted 2Listening exercise ted 2
Listening exercise ted 2
 
Blubag brochure
Blubag brochureBlubag brochure
Blubag brochure
 
Presentatie Bart Vos & Margreet Kloppenburg Humanagement Relatiedag 11-10-2012
Presentatie Bart Vos & Margreet Kloppenburg Humanagement Relatiedag 11-10-2012Presentatie Bart Vos & Margreet Kloppenburg Humanagement Relatiedag 11-10-2012
Presentatie Bart Vos & Margreet Kloppenburg Humanagement Relatiedag 11-10-2012
 
Listening exercise ted 2
Listening exercise ted 2Listening exercise ted 2
Listening exercise ted 2
 
Giffords
GiffordsGiffords
Giffords
 
Banda Marcial
Banda MarcialBanda Marcial
Banda Marcial
 
Interactive tv fri123 7
Interactive tv fri123 7Interactive tv fri123 7
Interactive tv fri123 7
 
Clothes
ClothesClothes
Clothes
 
Enabling Opinion-Driven Decision Making - Sentiment Analysis Innovation Summit
Enabling Opinion-Driven Decision Making - Sentiment Analysis Innovation Summit Enabling Opinion-Driven Decision Making - Sentiment Analysis Innovation Summit
Enabling Opinion-Driven Decision Making - Sentiment Analysis Innovation Summit
 
Supermarket
SupermarketSupermarket
Supermarket
 

Similaire à Opinion-Based Entity Ranking

Preference Elicitation Interface
Preference Elicitation InterfacePreference Elicitation Interface
Preference Elicitation Interface
晓愚 孟
 
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
OpenSource Connections
 
Rated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: An Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Alessandro Benedetti
 
Mining Product Reputations On the Web
Mining Product Reputations On the WebMining Product Reputations On the Web
Mining Product Reputations On the Web
feiwin
 
MLConf - Emmys, Oscars & Machine Learning Algorithms at Netflix
MLConf - Emmys, Oscars & Machine Learning Algorithms at NetflixMLConf - Emmys, Oscars & Machine Learning Algorithms at Netflix
MLConf - Emmys, Oscars & Machine Learning Algorithms at Netflix
Xavier Amatriain
 
2005 Web Content Mining 4
2005 Web Content Mining   42005 Web Content Mining   4
2005 Web Content Mining 4
George Ang
 

Similaire à Opinion-Based Entity Ranking (20)

Collaborative Filtering Recommendation System
Collaborative Filtering Recommendation SystemCollaborative Filtering Recommendation System
Collaborative Filtering Recommendation System
 
In situ evaluation of entity retrieval and opinion summarization
In situ evaluation of entity retrieval and opinion summarizationIn situ evaluation of entity retrieval and opinion summarization
In situ evaluation of entity retrieval and opinion summarization
 
Online feedback correlation using clustering
Online feedback correlation using clusteringOnline feedback correlation using clustering
Online feedback correlation using clustering
 
Preference Elicitation Interface
Preference Elicitation InterfacePreference Elicitation Interface
Preference Elicitation Interface
 
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: an Open Source Approach for Search Quality Evaluation
 
Overview of recommender system
Overview of recommender systemOverview of recommender system
Overview of recommender system
 
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
Haystack 2019 - Rated Ranking Evaluator: an Open Source Approach for Search Q...
 
Rated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: An Open Source Approach for Search Quality EvaluationRated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
Rated Ranking Evaluator: An Open Source Approach for Search Quality Evaluation
 
Developing Movie Recommendation System
Developing Movie Recommendation SystemDeveloping Movie Recommendation System
Developing Movie Recommendation System
 
Towards a Quality Assessment of Web Corpora for Language Technology Applications
Towards a Quality Assessment of Web Corpora for Language Technology ApplicationsTowards a Quality Assessment of Web Corpora for Language Technology Applications
Towards a Quality Assessment of Web Corpora for Language Technology Applications
 
Opinion Driven Decision Support System
Opinion Driven Decision Support SystemOpinion Driven Decision Support System
Opinion Driven Decision Support System
 
Invited talk @Roma La Sapienza, April '07
Invited talk @Roma La Sapienza, April '07Invited talk @Roma La Sapienza, April '07
Invited talk @Roma La Sapienza, April '07
 
Mining Product Reputations On the Web
Mining Product Reputations On the WebMining Product Reputations On the Web
Mining Product Reputations On the Web
 
Recommendation engine Using Genetic Algorithm
Recommendation engine Using Genetic AlgorithmRecommendation engine Using Genetic Algorithm
Recommendation engine Using Genetic Algorithm
 
MLConf - Emmys, Oscars & Machine Learning Algorithms at Netflix
MLConf - Emmys, Oscars & Machine Learning Algorithms at NetflixMLConf - Emmys, Oscars & Machine Learning Algorithms at Netflix
MLConf - Emmys, Oscars & Machine Learning Algorithms at Netflix
 
Xavier amatriain, dir algorithms netflix m lconf 2013
Xavier amatriain, dir algorithms netflix m lconf 2013Xavier amatriain, dir algorithms netflix m lconf 2013
Xavier amatriain, dir algorithms netflix m lconf 2013
 
Online Learning to Rank
Online Learning to RankOnline Learning to Rank
Online Learning to Rank
 
2005 Web Content Mining 4
2005 Web Content Mining   42005 Web Content Mining   4
2005 Web Content Mining 4
 
ppt.pptx
ppt.pptxppt.pptx
ppt.pptx
 
Movie recommendation Engine using Artificial Intelligence
Movie recommendation Engine using Artificial IntelligenceMovie recommendation Engine using Artificial Intelligence
Movie recommendation Engine using Artificial Intelligence
 

Dernier

Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
UXDXConf
 

Dernier (20)

IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptxIOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
IOS-PENTESTING-BEGINNERS-PRACTICAL-GUIDE-.pptx
 
Powerful Start- the Key to Project Success, Barbara Laskowska
Powerful Start- the Key to Project Success, Barbara LaskowskaPowerful Start- the Key to Project Success, Barbara Laskowska
Powerful Start- the Key to Project Success, Barbara Laskowska
 
Introduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG EvaluationIntroduction to Open Source RAG and RAG Evaluation
Introduction to Open Source RAG and RAG Evaluation
 
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptxWSO2CONMay2024OpenSourceConferenceDebrief.pptx
WSO2CONMay2024OpenSourceConferenceDebrief.pptx
 
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptxUnpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
Unpacking Value Delivery - Agile Oxford Meetup - May 2024.pptx
 
Demystifying gRPC in .Net by John Staveley
Demystifying gRPC in .Net by John StaveleyDemystifying gRPC in .Net by John Staveley
Demystifying gRPC in .Net by John Staveley
 
Server-Driven User Interface (SDUI) at Priceline
Server-Driven User Interface (SDUI) at PricelineServer-Driven User Interface (SDUI) at Priceline
Server-Driven User Interface (SDUI) at Priceline
 
IESVE for Early Stage Design and Planning
IESVE for Early Stage Design and PlanningIESVE for Early Stage Design and Planning
IESVE for Early Stage Design and Planning
 
ECS 2024 Teams Premium - Pretty Secure
ECS 2024   Teams Premium - Pretty SecureECS 2024   Teams Premium - Pretty Secure
ECS 2024 Teams Premium - Pretty Secure
 
Exploring UiPath Orchestrator API: updates and limits in 2024 🚀
Exploring UiPath Orchestrator API: updates and limits in 2024 🚀Exploring UiPath Orchestrator API: updates and limits in 2024 🚀
Exploring UiPath Orchestrator API: updates and limits in 2024 🚀
 
Structuring Teams and Portfolios for Success
Structuring Teams and Portfolios for SuccessStructuring Teams and Portfolios for Success
Structuring Teams and Portfolios for Success
 
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMsTo Graph or Not to Graph Knowledge Graph Architectures and LLMs
To Graph or Not to Graph Knowledge Graph Architectures and LLMs
 
Enterprise Security Monitoring, And Log Management.
Enterprise Security Monitoring, And Log Management.Enterprise Security Monitoring, And Log Management.
Enterprise Security Monitoring, And Log Management.
 
PLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. StartupsPLAI - Acceleration Program for Generative A.I. Startups
PLAI - Acceleration Program for Generative A.I. Startups
 
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
Integrating Telephony Systems with Salesforce: Insights and Considerations, B...
 
UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1UiPath Test Automation using UiPath Test Suite series, part 1
UiPath Test Automation using UiPath Test Suite series, part 1
 
Connecting the Dots in Product Design at KAYAK
Connecting the Dots in Product Design at KAYAKConnecting the Dots in Product Design at KAYAK
Connecting the Dots in Product Design at KAYAK
 
10 Differences between Sales Cloud and CPQ, Blanka Doktorová
10 Differences between Sales Cloud and CPQ, Blanka Doktorová10 Differences between Sales Cloud and CPQ, Blanka Doktorová
10 Differences between Sales Cloud and CPQ, Blanka Doktorová
 
Connector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a buttonConnector Corner: Automate dynamic content and events by pushing a button
Connector Corner: Automate dynamic content and events by pushing a button
 
A Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System StrategyA Business-Centric Approach to Design System Strategy
A Business-Centric Approach to Design System Strategy
 

Opinion-Based Entity Ranking

  • 1. Ganesan & Zhai 2012, Information Retrieval, Vol 15, Number 2 Kavita Ganesan (www.kavita-ganesan.com) University of Illinois @ Urbana Champaign Journal Project Page
  • 2. Currently: No easy or direct way of finding entities (e.g. products, people, businesses) based on online opinions  You need to read opinions about different entities to find entities that fulfill personal criteria e.g. finding mp3 players with ‘good sound quality’
  • 3. Currently: No easy or direct way of finding entities (e.g. products, people, businesses) based on online opinions  You need to read opinions about different entities to find entities that fulfill personal criteria  (e.g. finding mp3 players with ‘good sound quality’ Time consuming process & impairs user productivity!
  • 4. Use existing opinions to rank entities based on a set of unstructured user preferences  Example of user preferences:  Finding a hotel: “clean rooms, heated pools”  Finding a restaurant: “authentic food, good ambience”
  • 5. Most obvious way: use results of existing opinion mining methods  Find sentiment ratings on various aspects ▪ For example, for an mp3 player: find ratings for screen, sound, battery life aspects ▪ Then, rank entities based on these discovered aspect ratings  Problem is that this is Not practical! ▪ Costly – It is costly to mine large amounts of textual content ▪ Prior knowledge – You need to know the set of queriable aspects in advance. So, you may have to define aspects for each domain either manually or through text mining ▪ Supervision – Most of the existing methods rely on some form of supervision like the presence of overall user ratings. Such information may not always be available.
  • 6. Leverage Existing Text Retrieval Models  Why?  Retrieval models can scale up to large amounts of textual content  The models themselves can be tweaked or redefined  This does not require costly information extraction or text mining
  • 7. Leveraging robust text retrieval models Indexed rank Entity 1 Entity 1 Reviews rank retrieval User Preferences Entity 2 models (query) Entity 2 Reviews (BM25, LM, PL2) rank Entity 3 Entity 3 Reviews Keyword match between user prefs & textual reviews
  • 8. Leveraging robust text retrieval models Indexed rank Entity 3 Entity 3 Reviews rank retrieval User Preferences Entity 2 models (query) Entity 2 Reviews (BM25, LM, PL2) rank Entity 1 Entity 1 Reviews Keyword match between user prefs & textual reviews
  • 9. Based on the basic setup, this ranking problem seems similar to regular document retrieval problem  However, there are important differences: 1. The query is meant to express a user's preferences in keywords  Query is expected to be longer than regular keyword queries  Query may contain sub-queries expressing preferences for different aspects  It may actually be beneficial to model these semantic aspects 2. Ranking is to capture how well an entity satisfies a user's preferences  Not the relevance of a document to a query (as in regular retrieval)  The matching of opinion/sentiment words would be important in this case
  • 10. Investigate use of text retrieval models for the task of Opinion-Based Entity Ranking  Explore some extensions over IR models  Propose evaluation method for the ranking task  User Study  To determine if results make sense to users  Validate effectiveness of evaluation method
  • 11. In standard text retrieval we cannot distinguish the multiple preferences in a query. For example: “clean rooms, cheap, good service”  Would be treated as a long keyword query even though there are 3 preferences in the query  Problem with this is that an entity may score highly because of matching one aspect extremely well  To improve this:  We try to score each preference separately and then combine the results
  • 12. Aspect Queries “clean rooms, cheap, “good “clean rooms” “cheap” service” good service” scored retrieval model separately retrieval model result set 1 result set 2 result set 3 Results results Results combined
  • 13. In standard retrieval models the matching of an opinion word & a standard topic word is not distinguished  However, with Opinion-Based Entity Ranking:  It is important to match opinion words in the query, but opinion words tend to have more variation than topic words  Solution: Expand a query with similar opinion words to help emphasize the matching of opinions
  • 14. Similar Meaning to Fantastic battery life “Fantastic battery life” Query Good battery life Great battery life Excellent battery life Review documents
  • 15. Similar Meaning to Fantastic battery life “Fantastic battery life” Query Add synonyms of Good battery life word “fantastic” Fantastic, good, Great battery life great,excellent… battery life Excellent battery life Expanded Query Review documents
  • 16. Document Collection  Gold Standard: Relevance Judgement  User Queries  Evaluation Measure
  • 17. Document Collection:  Reviews of Hotels – Tripadvisor  Reviews of Cars – Edmunds Numerical aspect ratings Gold standard Free text reviews
  • 18. Gold Standard:  Needed to asses performance of ranking task  For each entity & for each aspect (in dataset):  Average numerical ratings across reviews. This will give the judgment score for each aspect  Assumption: Since the numerical ratings were given by users, this would be a good approximation to actual human judgment
  • 19. Gold Standard: Ex. User looking for cars with “good performance”  Ideally, the system should return cars with ▪ High numerical ratings on performance aspect ▪ Otherwise, we can say that the system is not doing well in ranking Should have high ratings on performance
  • 20. User Queries  Semi synthethic queries  Not able to obtain natural sample of queries  Ask users to specify preferences on different aspects of car & hotel based on aspects available in dataset ▪ Seed queries ▪ Ex. Fuel: “good gas mileage”, “great mpg”  Randomly combine seed queries from different aspects  forms synthetic queries ▪ Ex. Query 1: “great mpg, reliable car” ▪ Ex. Query 2: “comfortable, good performance”
  • 21. Evaluation Measure: nDCG  This measure is ideal because it is based on multiple levels of ranking  The numerical ratings used as judgment scores has a range of values and nDCG will actually support this.
  • 22. Users were asked to manually determine the relevance of system generated rankings to a set of queries Two reasons for user study:  Validate that results made sense to real users  On average, users thought that the entities retrieved by the system were a reasonable match to the queries  Validate effectiveness of gold standard rankings  Gold standard ranking has relatively strong agreement with user rankings. This means the gold standard based on numerical ratings is a good approximation to human judgment
  • 23. Most effective Most effective on BM25 (p23) on BM25 (p23) 8.0% Hotels 2.5% Cars 6.0% 2.0% 1.5% 4.0% 1.0% 2.0% 0.5% 0.0% 0.0% PL2 LM BM25 PL2 LM BM25 QAM QAM + OpinExp QAM QAM + OpinExp Improvement in ranking using QAM Improvement in ranking using QAM + OpinExp
  • 24. Lightweight approach to ranking entities based on opinions  Use existing text retrieval models  Explored some enhancements over retrieval models  Namely opinion expansion & query aspect modeling  Both showed some improvement in ranking  Proposed evaluation method using user ratings  User study shows that the evaluation method is sound  This method can be used for future evaluation tasks

Notes de l'éditeur

  1. So this long keyword query will be split into 3 separate queries. Each called an aspect query.These aspect queries are scored separately and the results are then combined.
  2. -
  3. -for each entity, average the numerical ratings of each aspect-assumption: this would be a good approximation to human judgment
  4. Otherwise, this tells you that the system is not really doing well in ranking.
  5. -could not obtain natural queries, so we used semi synthetic queries.-what we did was-and then we randomly combined queries…to form a set of queries.
  6. Then finally we conducted a user study where users were asked to manually determine the relevance of the the sysGen results to query. This is to validate that the results made sense to real usersAnd also to validate the effectiveness of the gold standard rankings which is based on the…Based on this we found that…Which means that this evaluation method can be safely used for similar ranking tasks…