Searching for restaurants on the current Zomato app is purely based on dish and restaurant names. Our goal at the end of this project is to provide a recommendation system not limited by these constraints. We want the user to be able to write down what they are searching for in a restaurant and based on these requirements provide users with the restaurants with their criteria.
To determine the facilities provided by the restaurant at the customer level we will be making use of customer reviews as they best represent what someone can expect at a restaurant. For example, if one types in ‘Fun Outings’ we want to be able to display all restaurants that may cater to this need and display them to the user
The following libraries are required to run the code:
- Numpy
- Pandas
- Sklearn
- Seaborn
- Matplotlib
- Plotly
- Wordcloud
- Nltk
- Keras
- Tensorflow
- Genism
Dataset source : The dataset ‘Zomato Bangalore Restaurants’ is publicly available on the Kaggle website.
Dataset size : Our dataset contains 5171 rows entries and 17 attributes
Dataset link: https://www.kaggle.com/datasets/himanshupoddar/zomato-bangalore-restaurants
- Knowledge Based Recommender system
- Content Based Recommender System
- Content Based Recommender System for Search Query
- LDA(Latent Dirichlet Allocation) Model
[1] Elham Asani, Hamed Vahdat-Nejad, Javad Sadri, Restaurant recommender system based on sentiment analysis,Machine Learning with Applications,Volume 6, 2021, 100114,ISSN 2666-8270
[2] Alif Azhar Fakhri et al 2019 J. Phys.: Conf. Ser. 1192 012023 "Restaurant Recommender System Using User-Based Collaborative Filtering Approach: A Case Study at Bandung Raya Region"
[3] Pedersen, T., Patwardhan, S., & Michelizz, J. (2004). WordNet::Similarity-measuring the relatedness of concepts. In19th national conference on artificial intelligence. San Jose, CA, USA.
[4] Choenyi, T. et al. "A Review on Filtering Techniques Usedin Restaurant Recommendation System." International Journal of Computer Science and Mobile Computing 10.4 113-117.
[5] Gupta A and Singh K 2013 Location based personalized restaurant recommendation system for mobile environments Advances in Computing, Communications and Informatics pp. 507-511 IEEE
https://towardsdatascience.com/latent-dirichlet-allocation-lda-9d1cd064ffa2
https://arxiv.org/pdf/1301.3781.pdf
https://www.oreilly.com/library/view/natural-language-annotation/9781449332693/ch01.html