Combining Rating and Review Data by Initializing Latent Factor Models with Topic Models for Top-N Recommendation

Pena, Francisco José Ribadas; O'Reilly-Morgan, Diarmuid; Τράγος, Ηλίας; Hurley, Neil; Duriakova, Erika; Smyth, Barry; Lawlor, Aonghus

doi:10.1145/3383313.3412207

Cited by 18 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the works by Musto, Narducci, Lops, De Gemmis, andSemeraro (2016), andSansonetti, Gasparetti, Micarelli, Cena, andGena (2019), we find out other kinds of knowledge sources to implement explanations, like Linked Open Data (LOD). The proposals by Lu, Dong, and Smyth (2018) and Peña, O'Reilly-Morgan, Tragos, Hurley, Duriakova, Smyth, and Lawlor (2020) describe innovative models to mix textual information from user reviews and knowledge from matrix factorization to make explanations. These four works noticed us a wide variety of knowledge sources used in explanation systems.…”

Section: Explanation Approachesmentioning

confidence: 99%

Conceptual Modeling of Explainable Recommender Systems: An Ontological Formalization to Guide Their Design and Development

Caro-Martínez

Jiménez-Díaz

Recio-García³

2021

jair

View full text Add to dashboard Cite

With the increasing importance of e-commerce and the immense variety of products, users need help to decide which ones are the most interesting to them. This is one of the main goals of recommender systems. However, users’ trust may be compromised if they do not understand how or why the recommendation was achieved. Here, explanations are essential to improve user confidence in recommender systems and to make the recommendation useful. Providing explanation capabilities into recommender systems is not an easy task as their success depends on several aspects such as the explanation’s goal, the user’s expectation, the knowledge available, or the presentation method. Therefore, this work proposes a conceptual model to alleviate this problem by defining the requirements of explanations for recommender systems. Our goal is to provide a model that guides the development of effective explanations for recommender systems as they are correctly designed and suited to the user’s needs. Although earlier explanation taxonomies sustain this work, our model includes new concepts not considered in previous works. Moreover, we make a novel contribution regarding the formalization of this model as an ontology that can be integrated into the development of proper explanations for recommender systems.

show abstract

Section: Explanation Approachesmentioning

confidence: 99%

Conceptual Modeling of Explainable Recommender Systems: An Ontological Formalization to Guide Their Design and Development

Caro-Martínez

Jiménez-Díaz

Recio-García³

2021

jair

View full text Add to dashboard Cite

show abstract

“…With the increase in feedback to published items, researchers are increasingly focusing on how to integrate the topic model and sentiment analysis of reviews in feedback into recommendation. First, researchers have tried to use the topic model to directly impact the generation process of the latent factors of MF methods [11,2,3,15,18]. The methods of [11,2] transform the topic distribution of reviews by LDA to latent factors of MF, while the method of [3] aligns learning rates of MF by using the topic distribution.…”

Section: Related Workmentioning

confidence: 99%

“…The methods of [11,2] transform the topic distribution of reviews by LDA to latent factors of MF, while the method of [3] aligns learning rates of MF by using the topic distribution. The method proposed by Peña et al [15] uses the topic distribution of reviews for the initialization of the latent factors of MF. The method proposed by Shoja et al [18] uses the topic distribution by LDA to extract user attributes related to each item category, and construct the user attributes matrix separately from the user-item matrix.…”

Section: Related Workmentioning

confidence: 99%

Matrix Factorization with Topic and Sentiment Analysis for Rating Prediction

Wang

Fang

Kamei

2021

IJNC

View full text Add to dashboard Cite

In today's online services, users' feedback such as numerical rating, textual review, time of purchase, and so on for each item is often encouraged to provide. Managers of online services utilize the feedback to improve the quality of their services, or user experience. For example, many recommender systems predict the items that the users may like and purchase in the future using users' historical ratings. With the increase of user data in the systems, more detailed and interpretable information about item features and user sentiments can be extracted from textual reviews that are relative to ratings. In this paper, we propose a novel topic and sentiment matrix factorization model, which leverages both topic and sentiment drawn from the reviews simultaneously. First, we conduct topic analysis and sentiment analysis of reviews using Latent Dirichlet Allocation (LDA) and lexicon construction technique, respectively. Second, we combine the user consistency, which is calculated from his/her reviews and ratings, and helpful votes from other users of reviews to obtain a reliability measure to weight the ratings. Third, we integrate these three parts into the matrix factorization framework for the prediction of ratings. Our experimental comparison using Amazon datasets indicates that the proposed method significantly improves performance compared to traditional matrix factorization up to 14.12%.

show abstract

“…However, review-based recommender systems support a one-to-one type of matching between users and items. For example, in [10,12,22,29], the user model is instantiated on the basis of the reviews (s)he posts. Moreover, the item model depends on the overall amount of reviews it collects.…”

Section: Related Work 21 Recommender Systemsmentioning

confidence: 99%

“…In Content-Based Filtering, item features are typically extracted from textual catalogs by applying statistical metrics like TF-IDF. Moreover, in review-based recommender systems, opinion mining techniques such as faceted opinion extraction [26], bi-gram and trigram analysis [11], Non-negative Matrix Factorization [5], Latent Dirichlet Allocation (LDA) [2,25] and ensemble methods [29] are used to identify aspects in reviews. Further techniques are applied in the extraction of sentiment about products and services.…”

Section: Feature Extraction Techniquesmentioning

confidence: 99%

Beyond Traditional Cultural Heritage Recommender Systems: Suggesting Airbnb Experiences to Users

Mauro

Ardissono

Petrone

et al. 2021

Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization

View full text Add to dashboard Cite

Traditional recommender systems suggest Cultural and Natural Heritage items to visitors by matching the target user to the available options, one-to-one. However, the increasing diffusion of informal activities and events, supported by location-based services such as Airbnb, extends personalized recommendation to a manyto-one match-making task. Airbnb experiences, which any citizen can propose to offer geographic tours and thematic activities, are composed of at least two entities to be evaluated: the former is the experience itself (in terms of topic, cost, etc.); the latter is the host, who directly interacts with guests during the management of the planned activities. As both entities can dramatically influence guests' perceptions, they should be jointly taken into account by recommender systems. This paper presents our preliminary work aimed at extending the personalized suggestion of Cultural Heritage items to such composite objects. CCS CONCEPTS• Information systems → Web searching and information discovery; Recommender systems.

show abstract

Combining Rating and Review Data by Initializing Latent Factor Models with Topic Models for Top-N Recommendation

Cited by 18 publications

References 27 publications

Conceptual Modeling of Explainable Recommender Systems: An Ontological Formalization to Guide Their Design and Development

Conceptual Modeling of Explainable Recommender Systems: An Ontological Formalization to Guide Their Design and Development

Matrix Factorization with Topic and Sentiment Analysis for Rating Prediction

Beyond Traditional Cultural Heritage Recommender Systems: Suggesting Airbnb Experiences to Users

Contact Info

Product

Resources

About