Restaurant recommender system based on sentiment analysis

Asani, Elham; Vahdat-Nejad, Hamed; Sadri, Javad

doi:10.1016/j.mlwa.2021.100114

Cited by 53 publications

(25 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, if emotion information is to be reflected in the recommendation, scaling becomes problematic as it is not ordinal but categorical, suggesting that a new method should be considered because a native linear combination faces the lack of the effectiveness in recommendation due to the dimension difference of multiple relations. Previous studies have shown that sentiment or emotion information improves recommendation performance [1,3,4,20,21]. To the best of our knowledge, however, no studies have used both of these two in combination for recommender systems.…”

Section: Related Workmentioning

confidence: 99%

Improving Graph-Based Movie Recommender System Using Cinematic Experience

Lee¹,

Han²,

Han³

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

With the advent of many movie content platforms, users face a flood of content and consequent difficulties in selecting appropriate movie titles. Although much research has been conducted in developing effective recommender systems to provide personalized recommendations based on customers’ past preferences and behaviors, not much attention has been paid to leveraging users’ sentiments and emotions together. In this study, we built a new graph-based movie recommender system that utilized sentiment and emotion information along with user ratings, and evaluated its performance in comparison to well known conventional models and state-of-the-art graph-based models. The sentiment and emotion information were extracted using fine-tuned BERT. We used a Kaggle dataset created by crawling movies’ meta-data and review data from the Rotten Tomatoes website and Amazon product data. The study results show that the proposed IGMC-based models coupled with emotion and sentiment are superior over the compared models. The findings highlight the significance of using sentiment and emotion information in relation to movie recommendation.

show abstract

Section: Related Workmentioning

confidence: 99%

Improving Graph-Based Movie Recommender System Using Cinematic Experience

Lee¹,

Han²,

Han³

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Restaurants recommendation is a hot topic among numerous recommendation applications that has attracted the interest of practitioners and researchers in recommender systems in recent years [1][2][3][4][5][6][7]. A number of restaurant recommender systems have utilized mobilebased context aware services as well as location-based approaches, for example, Chu and Wu [1] proposed a restaurant recommender system based on mobile context aware services to supply users with personalized restaurant recommendations.…”

Section: Related Workmentioning

confidence: 99%

“…The proposed system is validated by asking volunteers to rate the recommendation results using 14 distinct models representing different combinations of factors, and the results demonstrate that personal preferences are the most important factor influencing the decision-making process when it comes to where to dine. In another study, a context-aware restaurant recommender system is proposed by Asani et al [7]. The proposed system first applies natural language processing techniques to users' comments about restaurants to extract the desired food names.…”

Section: Related Workmentioning

confidence: 99%

“…Consumers, on the other hand, frequently find it time-consuming and difficult to extract meaningful information from the vast amount of online information available, making selecting a restaurant even more challenging. Giv-Volume 13, Number 4, 2022 en how people's lifestyles are changing as a result of their use of technology, an intelligent recommender system that recommends restaurants can be a good solution for consumers to assist them in finding a restaurant that fits their needs and preferences [1][2][3][4][5][6][7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Trust-Based Recommender System for Personalized Restaurants Recommendation

Shambour

Abualhaj

Abu-Shareha

2022

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Several online restaurant applications, such as TripAdvisor and Yelp, provide potential consumers with reviews and ratings based on previous customers’ experiences. These reviews and ratings are considered the most important factors that determine the customer’s choice of restaurants. However, the selection of a restaurant among many unknown choices is still an arduous and time- consuming task, particularly for tourists and travellers. Recommender systems utilize the ratings provided by users to assist them in selecting the best option from many options based on their preferences. In this paper, we propose a trust-based recommendation model for helping consumers select suitable restaurants in accordance with their preferences. The proposed model utilizes multi- criteria ratings of restaurants and implicit trust relationships among consumers to produce personalized restaurant recommendations. The experimental results based on a real-world restaurant dataset demonstrated the superiority of the proposed model, in terms of prediction accuracy and coverage, in overcoming the sparsity and new user problems when compared to other baseline CF-based recommendation algorithms.

show abstract

“…Currently, RS is implemented in several fields such as E-government, E-business, E-commerce, E-library, Elearning, E-tourism, E-resource, and E-group activity (Lu et al, 2015). The restaurant recommender system is part of E-tourism that focuses on providing similar menus based on price and taste (Burke, 2000), reputation (Fakhri et al, 2019), food quality and service (Asani et al, 2021), user's preference and location information (Zeng et al, 2016) and user reviews (Hassan and Abdulwahhab, 2017). Alhijawi and Kilani (2020) discovered that Collaborative Filtering (CF) is the most popular technique for analyzing historical user feedback information to predict recommendations.…”

Section: Introductionmentioning

confidence: 99%

The Exploration of Restaurant Recommender System

Fahrudin¹,

Wisna²

2022

Journal of Computer Science

View full text Add to dashboard Cite

The exploitation of Recommender Systems (RS) is still a challenge, hence it is important to explore the three correlated attributes, such as restaurant, food, and service ratings. Therefore, this study provides an indepth review of these attribute ratings using the Collaborative Filtering (CF) technique. Experiments were performed with k-NN, SVD, Slope One, and Co-Clustering algorithms, while RMSE, MSE, MAE, and FCP were used as evaluation metrics. The results showed that the service restaurant rating predictions produced the best average MSE and RMSE accuracy in 5 and 10fold cross-validation. Furthermore, the best hyperparameter of algorithms using Grid Search was achieved in restaurant rating prediction. In conclusion, SVD surpasses other algorithms in MSE and RMSE for all scenarios.

show abstract

Restaurant recommender system based on sentiment analysis

Cited by 53 publications

References 29 publications

Improving Graph-Based Movie Recommender System Using Cinematic Experience

Improving Graph-Based Movie Recommender System Using Cinematic Experience

A Trust-Based Recommender System for Personalized Restaurants Recommendation

The Exploration of Restaurant Recommender System

Contact Info

Product

Resources

About