Opinionated Product Recommendation

Dong, Ruihai; Schaal, Markus; O’Mahony, Michael P.; McCarthy, Kevin; Smyth, Barry

doi:10.1007/978-3-642-39056-2_4

Cited by 37 publications

(43 citation statements)

References 17 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Instead, it focuses on the technical properties and physical description of a product. To solve this problem, one can use product reviews which are generated from customers' experience with the products as a basis of product information in case-based recommendation [4], [5]. The purpose of using customer reviews is to enrich the informative product case base on the basis of feature opinions to optimize the matching of user's preferences.…”

Section: Customer-oriented Review Recommendationmentioning

confidence: 99%

“…3. There are four basic steps: (1) finding the beneficial product features, (2) connecting each feature with a sentiment score based on the content of user reviews, (3) generating product cases by combining the features and the sentiment scores, and (4) retrieving recommended cases given a target query [4], [5]. Feature extraction and sentiment calcu- Fig.…”

Section: Customer-oriented Review Recommendationmentioning

confidence: 99%

“…Each feature F i is linked to a set of positive, negative, or neutral sentiment labels which are used to calculate the feature-level sentiment score S ent(F i , P) as shown in Eq. (2) [4]; Pos(F i , P), Neg(F i , P), and Neut(F i , P) stand for the number of positive, negative, and neutral sentiment labels for feature F i . The overall sentiment of all product features S ent(P) is calculated as the average of the sentiment scores of each feature, as illustrated in Eq.…”

Section: Experience-based Casementioning

confidence: 99%

“…Case-based recommendation approaches, including conversational and critiquing-based recommenders, are limited in their usage of unified case descriptions centered on technical features. This type of case representation is not appropriate in any experiential context [4], [5]. On contrary, cases generated from reviews are experiential.…”

Section: Related Workmentioning

confidence: 99%

“…They both use similarity assessment as a foundation for query-product comparison, although the concept that product cases, which are usually fixed feature-based tuples, are experiential is not adopted well in case-based recommenders. To solve this problem as well as the recommenders' rating sparsity issue, one can use product reviews which are generated from users' experience with the product as a basis of product information [4], [5].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A New Sentiment Case-Based Recommender

Aldayel

Ykhlef

2017

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYRecommender systems have attracted attention in both the academic and the business areas. They aim to give users more intelligent methods for navigating and identifying complex information spaces, especially in e-commerce domain. However, these systems still have to overcome certain limitations that reduce their performance, such as overspecialization of recommendations, cold-start, and difficulties when items with unequal probability distribution exist. A novel approach addresses the above issues through a case-based recommendation methodology which is a form of content-based recommendation that is well suited to many product recommendation domains, owing to the clear organization of users' needs and preferences. Unfortunately, the experience-based roots of case-based reasoning are not clearly reflected in case-based recommenders. In other words, the concept that product cases, which are usually fixed feature-based tuples, are experiential is not adopted well in case-based recommenders. To solve this problem as well as the recommenders' rating sparsity issue, one can use product reviews which are generated from users' experience with the product a basis of product information. Our approach adapts the use of sentiment scores along with feature similarity throughout the recommendation unlike traditional case-based recommender systems, which tend to depend entirely on pure similarity-based approaches. This paper models product cases with the products' features and sentiment scores at the feature level and product level. Thus, combining user experience and similarity measures improves the recommender performance and gives users more flexibility to choose whether they prefer products more similar to their query or better qualified products. We present the results using different evaluation methods for different case structures, different numbers of similar cases retrieved and multilevel sentiment-approaches. The recommender performance was highly improved with the use of feature-level sentiment approach, which recommends product cases that are similar to the query but favored for customers. key words: recommenders, case-based reasoning (CBR), case-based recommenders, opinion mining

show abstract

Section: Customer-oriented Review Recommendationmentioning

confidence: 99%

Section: Customer-oriented Review Recommendationmentioning

confidence: 99%

Section: Experience-based Casementioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations