• Save
A Multidomain and Multilingual Conceptual Data Model for Online Reviews Representation
Upcoming SlideShare
Loading in...5
×
 

A Multidomain and Multilingual Conceptual Data Model for Online Reviews Representation

on

  • 359 views

User-Generated Content (UGC) such as online reviews are freely available in the web. This kind of data has ...

User-Generated Content (UGC) such as online reviews are freely available in the web. This kind of data has
been used to support clients’ and managerial decision making in several industries, e.g. books, tourism or
hospitality. However, the challenge is how to represent this information in a structured way in order to
leverage on the information provided by the use of Web 2.0 applications. To deal with this challenge,
models and metamodels have been used to support a set of concrete applications in several sub-domains into
Computer Science and Information Systems body of knowledge (Karagiannis and Höfferer, 2006). This
paper focuses on the model-driven engineering and introduces a new multidomain and multilingual
conceptual data model to represent UGC. This model is based on a characterization of online reviews and
aims to capture all the facets of these reviews. The characterization of the reviews’ sentences extends
previous models (such as Martin and White, 2007; Ding et al., 2008; Liu, 2010). Applications build on the
model proposed in this paper may allow in-depth analysis of the fine-grained and disperse knowledge
existent in the UGC. Furthermore, as this model is domain-independent it can be used to represent multiple
types of reviews.

Statistics

Views

Total Views
359
Views on SlideShare
359
Embed Views
0

Actions

Likes
0
Downloads
0
Comments
0

0 Embeds 0

No embeds

Accessibility

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment
  • An objective sentence contains or mention facts.This hotel is far from the airport, ca. 15km.A subjective sentence does not mention any fact.The parking could be free.It describes how intense it was the experience using a product or service:very positive, positive, neutral, negative and very negative. Very kindly staff. refers to a very positive impression on the staff service.
  • 4.1 AffectIt refers to a personal emotional state (happiness, sad and angry), and is the most explicitly subjective type of appraisal (Whitelaw et al. 2005). “I was very happy for spend the holiday in this comfortable hotel.” expresses a happiness sentiment. 4.2 AppreciationIt refers to the intrinsic object properties (dirty, cold and small).4.3 JudgmentIt refers to an opinion formed by judging other’s behaviour (“attentive staff” and “friendly waiter”).
  • 6.1 Explicit Suggestion - direct mentionFor example, in a hotel service, an explicit suggestion is “The mattresses of the beds need to be exchanged”.6.2 Implicit SuggestionIt is an indirect mention on a need of the product or service. For example, in a hotel service, an implicit suggestion is “… does not offer Internet service”.
  • An intention can be also considered as an implicit recommendation! If we get the chance to Roma again we will ensure that we stay at the Alpha Hotel again.

A Multidomain and Multilingual Conceptual Data Model for Online Reviews Representation A Multidomain and Multilingual Conceptual Data Model for Online Reviews Representation Presentation Transcript

  • ICSOFT 20127th International Conference on Software Paradigm Trends A Multidomain and Multilingual Conceptual Data Model for Online Reviews Representation Marcirio Silveira Chaves Business and Information Technology Research Centre (BITREC) UniversidadeAtlântica, Portugal marcirio.chaves@uatlantica.pt WinniePicoto School of Economics and Management Technical University of Lisbon, Portugal w.picoto@iseg.utl.pt
  • Research Question How to capture the different facets of online reviews in an usable knowledge representation? Solution approachA new multidomain and multilingual conceptual data model for capturing and storing knowledge from opinionated texts.July 30, 2012 ICSOFT 2012 2
  • Outline• Characterization ofUser-Generated Content• Problem Scenario• Model-driven Engineering - Modeling UGC• Final RemarksJuly 30, 2012 ICSOFT 2012 3
  • Characterization of UGC1 - Object (O) – An object is a product (e.g. movie and book) or a service (e.g. hotel and restaurant) under review which is composed by features. – Objects a.k.a. entities.2 - Feature (F) – A feature is a component or part of an object. • actor and photography are features on a movie. • pool and staff are features on a hotel. – Features a.k.a. attributes or facets.July 30, 2012 ICSOFT 2012 4
  • Characterization of UGC3 - Sentence-Orientation (SO) – A review consists of a sequence of sentencesr=〈 s1, s2, …, sm〉(Ding et al., 2008).3.1 Objectivity – An objective sentencecontains or mention facts. – A subjective sentencedoes not mention any fact.3.2 Positivity – Orientation present in a sentence (+, -, or neutral).3.3 Intensity (strength of the positivity) – Strengthof the private state that is being expressed. – How strong is an emotion or a conviction of belief (Wilson, 2008). July 30, 2012 ICSOFT 2012 5
  • Characterization of UGC4 - Attitude (A) – Appraisal Theory (Martin and White, 2005) • how subjective language is used to express an attitude of some kind towards some target. – Appraisal Theory specifies three attitude types: • Affect(personal emotional state) • Appreciation(evaluation of phenomena) • Judgment(social or ethical appraisal of other’s behaviour)July 30, 2012 ICSOFT 2012 6
  • Characterization of UGC5 - Recommendation (R) – A recommendation is a positive or negative statement which explicitly mention in words the satisfaction of a consumer. • I recommend! and • If you plan to travel there, find another hotel closer to the main area, cause this ones not at all worth it!6 - Suggestion (SG) – A hint given by the holder in order to improve the object (i.e. service or product). 6.1 Explicit Suggestion - direct mention 6.2 Implicit Suggestion -indirect mentionJuly 30, 2012 ICSOFT 2012 7
  • Characterization of UGC7 - Intention (I) – It is a mention in which a holder explicitly intends (or not) to experiment again some product or service. 7.1 Positive Intention • When I come back to Roma, I intend to stay there myself. 7.2 Negative Intention • Certainly, we won’t repeat.July 30, 2012 ICSOFT 2012 8
  • Characterization of UGC8 - Complain (C): It is a phrase expressing a feeling of dissatisfaction, or resentment. – It is stronger than a suggestion.9 - Opinion Holder (H) – The holder of a particular opinion is the person or the organizationthat holds the opinion (Ding et al., 2008). – Demographiccharacteristics(e.g. name, city and country).10 – Source (S) – An information source is a web site which provides a set of reviews. • tripadvisor.com, booking.com, amazon.com July 30, 2012 ICSOFT 2012 9
  • Problem ScenarioQuestions on the context of managerial decision making: – Which online reviews make recommendations? Which of them are explicit? – What types of holders give more (positive and negative) suggestions? – What is the most frequent semantic orientation in online reviews written in Italian? – What are the verbs more often used to describe positive opinions on the features A, B and C? – What is the co-occurrence between attitudes and features?July 30, 2012 ICSOFT 2012 10
  • Model-driven Engineering• ModellingUGC – Requirements • To support multidomain and multilingual texts; • To support the storage and integration of multiple information sources; • To support fast and simple generation of managerial reports; • To allow a fine-grained storage of the online reviews’ content.July 30, 2012 ICSOFT 2012 11
  • Opinion Class Meta-model MultidomainJuly 30, 2012 ICSOFT 2012 12
  • Example• The view from the hotel room is wonderful - the ocean is just under the window! Liked the big swimming pool. The location is great, large beach near the hotel and if you like surfing, thats the place to go. Rating: 4 (1-5) August, 15 2010 - Group of friends, Russia.July 30, 2012 ICSOFT 2012 13
  • Review, Holder, Object, and Feature Model July 30, 2012 ICSOFT 2012 14
  • Example• The view from the hotel room is wonderful - the ocean is just under the window! Liked the big swimming pool. The location is great, large beach near the hotel and if you like surfing, thats the place to go. Rating: 4 (1-5) August, 15 2010 - Group of friends, Russia.July 30, 2012 ICSOFT 2012 15
  • Semantic orientation of the features in the sentencesJuly 30, 2012 ICSOFT 2012 16
  • Representation of co-occurrences detected in online reviewsJuly 30, 2012 ICSOFT 2012 17
  • Full conceptual data modelJuly 30, 2012 ICSOFT 2012 18
  • Final Remarks• A fine-grained characterization of online reviews.• A multidomain and multilingual conceptual data model to capture the different facets of unstructured online reviews.• Managers can explore historical data gathered.• Ongoing work – Development of algorithms to deal with semantic orientations, attitudes and recommendations in Portuguese. Chaves, M. S.; Freitas, L. A.; Souza, M. and Vieira, R. PIRPO: An Algorithm to deal with Polarity in Portuguese Online Reviews from the Accommodation Sector. Proc. of the 17th International Conference on Applications of Natural Language Processing to Information Systems (NLDB), Groningen, The Netherlands, 26-28 June. G. Bouma et al. (Eds.): NLDB 2012, LNCS 7337, pp. 296—301. Springer, Heidelberg, 2012. July 30, 2012 ICSOFT 2012 19