Using canonical correlation analysis for generalized sentiment analysis, product recommendation and search

Faridani, Siamak

doi:10.1145/2043932.2044005

Cited by 29 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The extracted terms can then be used to characterize the reviewer with a term-based user profile. In (Garcia Esparza et al 2010, 2011, the built profile is leveraged into the content-based approach to generate recommendations (see Sect. 4.1).…”

Section: Review Elementsmentioning

confidence: 99%

“…For instance, a term-based user profile can be built and used by the contentbased recommending approach (Garcia Esparza et al 2010, 2011. The virtual ratings inferred from reviews can take the role of real ratings in user-based or item-based CF (Leung et al 2006;Poirier et al 2010b;Zhang et al 2013).…”

Section: Algorithm Improvementmentioning

confidence: 99%

“…In our view, the feature opinions embedded in reviews might be used to infer multi-aspect ratings. For this purpose, Faridani (2011) has proven the effectiveness of a supervised learning model, Canonical Correlation Analysis (CCA) (Bach and Jordan 2005), for estimating multi-aspect ratings in a review. Additionally, in a situation in which multi-aspect ratings have already been specified by users, we believe that reviews could enhance these ratings, just as they can enhance overall ratings (see Sect.…”

Section: Future Trendsmentioning

confidence: 99%

See 2 more Smart Citations

Recommender systems based on user reviews: the state of the art

Chen

Wang

2015

User Model User-Adap Inter

341

187

View full text Add to dashboard Cite

In recent years, a variety of review-based recommender systems have been developed, with the goal of incorporating the valuable information in user-generated textual reviews into the user modeling and recommending process. Advanced text analysis and opinion mining techniques enable the extraction of various types of review elements, such as the discussed topics, the multi-faceted nature of opinions, contextual information, comparative opinions, and reviewers' emotions. In this article, we provide a comprehensive overview of how the review elements have been exploited to improve standard content-based recommending, collaborative filtering, and preference-based product ranking techniques. The review-based recommender system's ability to alleviate the well-known rating sparsity and cold-start problems is emphasized. This survey classifies state-of-the-art studies into two principal branches: review-based user profile building and review-based product profile building. In the user profile sub-branch, the reviews are not only used to create term-based profiles, but also to infer or enhance ratings. Multi-faceted opinions can further be exploited to derive the weight/value preferences that users place on particular features. In another sub-branch, the product profile can be enriched with feature opinions or comparative opinions to better reflect its assessment quality. The merit of each branch of work is discussed in terms of both algorithm development and the way in which the proposed

show abstract

Section: Review Elementsmentioning

confidence: 99%

Section: Algorithm Improvementmentioning

confidence: 99%

Section: Future Trendsmentioning

confidence: 99%

See 1 more Smart Citation

Recommender systems based on user reviews: the state of the art

Chen

Wang

2015

User Model User-Adap Inter

341

187

View full text Add to dashboard Cite

show abstract

“…This poses a challenge, requiring efficient algorithms to supply high quality recommendations to end users [2]. Faridani [10] trained a recommender model for an online clothes store, using textual and numerical ratings from the OpinionSpace dataset. Hanser et al [15] developed NewsViz giving numerical emotion ratings to words, calculating the emotional impact of words and paragraphs, which facilitates displaying the mood of the author over the course of online football reports.…”

Section: A Recommender Systemsmentioning

confidence: 99%

360-MAM-Affect: Sentiment Analysis with the Google Prediction API and EmoSenticNet

Mulholland¹,

Kevitt²,

Lunney³

et al. 2015

Proceedings of the 7th International Conference on Intelligent Technologies for Interactive Entertainment

View full text Add to dashboard Cite

show abstract

“…For example, Hardoon et al [15] used CCA to learn a semantic representation of web images and their associated text. Faridani [23] applied CCA to derive a model that combines text and numerical ratings on websites like Tripadvisor and Zappos and used it to predict numerical ratings from the text. And 5 There were 35,472 unique word in our data set.…”

Section: B Unsupervised Word Representation Learning With Canonical mentioning

confidence: 99%

Recommending Documents for Complex Question Exploration by Analyzing Collective Browsing Behavior

Asarina

Simek

2015

2015 48th Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Vast amounts of data available online and in other digital repositories make it challenging for users to find the right sources of information. In this paper, we present a novel approach for recommending documents to users by analyzing user browsing behavior, and demonstrate the effectiveness of our methods using an original data set.We conducted a study to collect a novel data set of document browsing behavior observed as users research complex questions. Based on this dataset, we developed machine learning algorithms to predict which documents are useful and should therefore be recommended.Following the intuition that useful documents are likely to be similar to other documents that are useful for the same task, we incorporated features based on measures of similarity between pairs of documents. Accurately computing similarity between documents is challenging due to the high dimensionality of bag-of-words representations (tens of thousands of dimensions). We therefore used several dimensionality reduction techniques, including Canonical Correlation Analysis, in order to project bag-of-words representations into meaningfully reduced spaces.We show that our algorithms significantly outperform baseline approaches on three different prediction tasks. Our work thus lays out a new direction for recommendation algorithms based on a relatively small amount of labeled data.

show abstract

Using canonical correlation analysis for generalized sentiment analysis, product recommendation and search

Cited by 29 publications

References 6 publications

Recommender systems based on user reviews: the state of the art

Recommender systems based on user reviews: the state of the art

360-MAM-Affect: Sentiment Analysis with the Google Prediction API and EmoSenticNet

Recommending Documents for Complex Question Exploration by Analyzing Collective Browsing Behavior

Contact Info

Product

Resources

About