This section of the paper is devoted to the overview of related works. The papers which are going to be dwelled upon below reflect upon mere recommendation systems, their types, as well as food recommendation systems. The conclusions which the authors of these papers have arrived at are to be summarized to be applied in further research.
In the article “Knowledge-based recommender system,” it is stated that the cognitive element is expected to be sufficient to dwell upon the similarity of the constituents. This type of system allows collecting data and evaluating it. However, it is possible to assert that the type can be applied as an additional system to other types (Burke 2013). The paper “Hydra: A Hybrid Recommender System” has considered the possibility of combining collaborative and content-based recommender systems, which is an innovative decision. The researchers arrived at an empirical conclusion that the system tends to provide a reliable outcome (Spiegel, Kunegis & Li 2009). The project report “Food Recommendation System” is devoted to content-based recommendation systems. These systems suggest that the user should try something by the information which is contained in the profile. The paper concludes that the knowledge-based systems which are also dwelled upon would have restricted application and fail to provide as much reliable information as content-based systems. However, the experiment was rather rough, so it needs further development and proof (Tatli 2009).
The paper “Food Recommendation using Ontology and Heuristics” considers various food recommender systems and gives an insight into a method of adaptive hypermedia. In the course of the research, different systems based on different methods have been discussed. It was revealed that word-based systems are more reliable than any other systems (El-Dosuky, Rashad, Hamza & EL-Bassiouny 2013). In the article “Food Recommendation System,” the researchers have aimed and finally managed to work out a system that would have a good outlook, as well as allow getting data about the most appropriate choice for the user. The experience might be used for the further development of the system (Gaikwad, Deshpande, Nalwar Katkar & Salave 2017). The paper “Using Cluster Database for Food Recommendation System” works out the system based on categorizing different alimentation elements to reveal the clients’ preferences and suggest an appropriate food group for them. The approach is expected to work better with more elements. However, the result which was received in the course of the experiment is reliable and can be used for the future elaboration of the corresponding system (Ravinarayana, Pooja, & Raghuveer 2016).
The article “Food Recommender System on Amazon” dwells upon a system for food stores and delicacies. The researchers have analyzed comments on amazon.com. Based on that, different systems, such as Linear Regression, Basic Latent Factor, Bias-SVD, and SVD++, were used to foresee whether people would appreciate the food or not. The conclusion is that the result is the most reliable in the case of the Linear Latent Factor (Huang, Zhou & Zhou 2013).
In the article “Group Recommender System for Restaurant Lunches,” the researchers have aimed to elaborate a corresponding system. The tool which has been used is a smartphone app for Android. Besides, an innovative method of data collection has been applied. First, individual recommendations are supposed to be revealed. Then they are intended to be analyzed. Hence, they are expected to result in group recommendations. Artificial intelligence mechanisms have been used for a proper analysis. The conclusion which the researchers have arrived at is that the system might come in handy only if it has so many elements that it is impossible to take into account all of them (Hallstorm 2013).
In the articles “Restaurant Recommendations for Facebook Users” and “A Preference-Based Restaurant Recommendation System for Individuals and Groups. Team Size: 3”, the researchers have concentrated on a recommendation system for restaurants. To ensure a reliable outcome and further efficient advice, they have collected required initial information from Facebook and Yelp, involved different artificial intelligence mechanisms, assessed the outcome in action, and analyzed the empirical data. They have concluded that artificial intelligence mechanisms might work better in locations that are often attended. Besides, they have revealed the possibility to envisage the connection between the location and clients (Han, Lin & Dai 2013, A preference-based restaurant recommendation system for individuals and groups. Team size: 3 2013). Besides, in the article “Yelp food recommendation system” an innovative approach based on “a metric which maximizes a minimum happiness” has been introduced (Sawant & Pai 2013, p. 4). It implies that users are proposed to reveal their preferences to the program, and the program is expected to suggest an appropriate restaurant for them. The result is 72% of content users, which proves the success of the research (Sawant & Pai 2013).
It is claimed to be important to establish a sort of communication between the user and the system to enable the system to find out the required information on the user’s alimentary inclinations. The information is supposed to be processed by the system, and the conclusion is expected to be drawn. The paper “Interaction Design in a Mobile Food Recommender System” mainly concentrates on the users’ long-term and short-term inclinations. It checks whether the system works or not. Based on the users’ overviews, the system under consideration gets high ranks (Elahi, Ge, Ricci, Fernandez-Tobias, Berkovsky & David 2015).
This section of the paper has been devoted to the overview of related works. The papers under consideration have concerned mere recommendation systems, their types, as well as food recommendation systems. The conclusions which the authors of these papers have arrived at have been to be summarized to be applied in further research.
Reference List
A preference-based restaurant recommendation system for individuals and groups. Team size: 3, 2013, Web.
Burke, R 2013,Knowledge-based recommender systems, Web.
El-Dosuky, M A, Rashad, M Z, Hamza, T T & EL-Bassiouny, A H 2013, Food recommendation using ontology and heuristics, Web.
Elahi, M, Ge, M, Ricci, F, Fernandez-Tobias, I, Berkovsky, S & David, M 2015, Interaction design in a mobile food recommender system, Web.
Hallstorm, E 2013,Group recommender system for restaurant lunches, Web.
Han, Q, Lin, V & Dai, W 2013, Restaurant recommendation for Facebook users, Web.
Huang, T, Zhou, H & Zhou, K 2013,Food recommender system on Amazon, Web.
Gaikwad, D S, Deshpande, A V, Nalwar N N, Katkar, M V & Salave A V 2017, Food recommendation system, Web.
Ravinarayana, A, Pooja, M C & Raghuveer, K 2016, Using clustered database for food recommendation system, Web.
Sawant, S & Pai, G 2013, Yelp food recommendation system, Web.
Spiegel, S, Kunegis, J & Li, F 2009, Hydra: A hybrid recommender system, Web.
Tatli, I 2009, Food recommendation system, Web.