Date post: | 24-May-2015 |
Category: |
Technology |
Upload: | kavita-ganesan |
View: | 2,630 times |
Download: | 0 times |
Opinion-Based Entity RankingGanesan & Zhai 2012, Information Retrieval, Vol 15, Number 2
Kavita Ganesan (www.kavita-ganesan.com)
University of Illinois @ Urbana ChampaignJournalProject Page
The problem
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 criteriae.g. finding mp3 players with ‘good sound quality’
The problem
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!
Proposed Idea
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”
How to rank entities based on opinions?
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.
Proposed Approach
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
The Basic Setup
Leveraging robust text retrieval models
Entity 1 Entity 1 Reviews
Entity 2 Entity 2 Reviews
Entity 3 Entity 3 Reviews
retrieval models
(BM25, LM, PL2)
User Preferences(query)
rank
rank
rank
Keyword matchbetween user prefs
& textual reviews
Indexed
The Basic Setup
Leveraging robust text retrieval models
Entity 3 Entity 3 Reviews
Entity 2 Entity 2 Reviews
Entity 1 Entity 1 Reviews
retrieval models
(BM25, LM, PL2)
User Preferences(query)
rank
rank
rank
Keyword matchbetween user prefs
& textual reviews
Indexed
Opinion Based Ranking vs. Document Retrieval
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
Focus of this work
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
Extension 1: Modeling Aspects in Query
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
Extension 1: Modeling Aspects in Query
“clean rooms” “cheap” “good service”
“clean rooms, cheap, good service”
retrieval model
Results
retrieval modelscored
separately
result set 1 result set 2 result set 3
Resultsresults
combined
Aspect Queries
Extension 2: Opinion Expansion
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
Extension 2: Opinion Expansion
Fantastic battery life
QueryGood battery life
Great battery life
Excellent battery life
Similar Meaning to “Fantastic battery life”
Review documents
Extension 2: Opinion Expansion
Fantastic, good, great,excellent…
battery life
Expanded Query
Good battery life
Great battery life
Excellent battery life
Similar Meaning to “Fantastic battery life”
Review documents
Fantastic battery life
QueryAdd synonyms of word “fantastic”
Evaluation of Ranking Task
Document Collection
Gold Standard: Relevance Judgement
User Queries
Evaluation Measure
Document Collection: Reviews of Hotels – Tripadvisor Reviews of Cars – Edmunds
Evaluation of Ranking Task
Free text reviews
Numerical aspect ratings
Gold standard
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
Evaluation of Ranking Task
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
Evaluation of Ranking Task
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 of Ranking Task
Evaluation of Ranking Task
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
User Study
Results: QAM & Opinion Expansion
PL2 LM BM250.0%1.0%2.0%3.0%4.0%5.0%6.0%7.0%8.0%9.0%
QAM QAM + OpinExp
PL2 LM BM250.0%
0.5%
1.0%
1.5%
2.0%
2.5%
QAM QAM + OpinExp
Hotels Cars
Improvement in ranking using QAMImprovement in ranking using QAM + OpinExp
Most effective on BM25 (p23)
Most effective on BM25 (p23)
Summary
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