Spot Recommendation System Research Articles

The HYBRID CONTENT-BASED FILTERING AND CLASSIFICATION RNN WITH PARTICLE SWARM OPTIMIZATION FOR TOURISM RECOMMENDATION SYSTEM

Economic recovery in the tourism sector after the COVID-19 pandemic is one of the main focuses of the Indonesian government at the moment, especially in Bandung City. This research aims to develop a personalized tourist spot recommendation system, by addressing the gaps in the existing literature through the integration of Content-Based Filtering (CBF) and Simple Recurrent Neural Network (RNN) methods that aim to improve recommendation accuracy. This study uses a hybrid approach that combines Term Frequency - Inverse Document Frequency (TF-IDF) and word embedding with the Robustly Optimized BERT (RoBERTa) model to identify similarities between tourist destinations based on their content characteristics. Simple RNN is used to analyze user preference patterns over time, which is then further optimized using Particle Swarm Optimization (PSO). As a result, the Simple RNN model that has been optimized with PSO shows an increased accuracy of up to 94.37%, outperforming other optimizations such as Adam and SGD. This research makes a novel contribution by applying advanced machine learning techniques to improve personalization in travel recommendation systems.

Machine Learning-Based Social Media Review Analysis for Recommending Tourist Spots

In recent years, the tourism industry has witnessed significant growth, resulting in an increased demand for effective and personalized tourist place recommendation systems. In this study, a tourist spot recommendation system is proposed which is built by developing a machine learning model based on a Support Vector Machine (SVM), Decision Tree (DT), and k-Nearest Neighbors(k-NN). Public experiences and opinions regarding the various spots available in popular social media sites such as TripAdvisor, Google, Instagram, and TikTok are utilized to train the model. The system matches the probability of the user query with the predicted probability of reviews for a particular spot. The SVM algorithm, known for its robustness in handling high-dimensional data, is adapted to model the complex relationships between users' reviews, spots, and their attributes. Real-world data is used to evaluate the system's performance, demonstrating its ability to significantly improve the user experience and contribute to the sustainable growth of the tourism sector. The system's capability was demonstrated as it achieved a notable F1-Score of 0.78 when SVM was implemented. Additionally, a promising accuracy rate of 93.023% was observed when random queries were used for tourism spot prediction, emphasizing that SVM outperformed DT and k-NN.

Analysis and Design of a Route Recommendation System and Bicycle Rental Fees at Tourist Destinations with Genetic Algorithms

The tourism sector is one of the country's most significant sources of income, especially in Indonesia. This is inseparable from many visitors or foreign tourists who come to Indonesia. Bandung is a tourist destination that is famous for its natural beauty and traditional culture, one example is in Desa Alamendah which has several tourist destinations, namely agro-tourism, nature tourism, and cultural tourism. However, access that can be passed from every tourist spot in Desa Alamendah can only be given on foot or by bicycle. Responding to this matter, bicycle facilities as a means of rotation are needed to access tourist attractions in Desa Alamendah. Based on these problems, this study aims to create a recommendation system for tourist attractions and bicycle rentals using an application in Desa Alamendah, Bandung. Using the Genetic Algorithm, an algorithm that can solve multi-objective problems can be applied to a tourist spot recommendation system in Desa Alamendah. In this system, the Genetic Algorithm is also used to determine fares based on the total distance traveled, so that bicycle rentals are more efficient. The study combines Google Maps as an appropriate route selection based on the recommendation of tourist destination points that tourists can visit using Genetic Algorithms, so that bicycle rentals are more efficient. This is study combines Google Maps as an appropriate route selection based on the recommendation of tourist destination points that tourists can visit using Genetic Algorithms. So that bicycle rentals are more efficient. The study combines Google Maps as an appropriate route selection based on the recommendation of tourist destination points that tourists can visit using Genetic Algorithms. Based on the results of tests that have been carried out in the process of forming tourist attractions recommendations with a Genetic Algorithm that using mutation probability 1.0 and Crossover Probability 0.6, can produce a Mobile Application with a Genetic Algorithm as a tourist spot recommendation system in Desa Alamendah. In addition, it also can provide recommendations, namely displaying tourist points, route using Google Maps. The rental fee is based on the total distance traveled.

A Sightseeing Spot Recommendation System That Takes into Account the Visiting Frequency of Users

The present study aimed to design, develop, operate and evaluate a sightseeing spot recommendation system that can efficiently and usefully support tourists while considering their visiting frequencies. This system was developed by integrating social networking services (SNSs), Web-geographic information systems (GIS) and recommendation systems. The system recommends sightseeing spots to users with different visiting frequencies, adopting two recommendation methods (knowledge-based recommendation and collaborative recommendation methods). Additionally, the system was operated for six weeks in Kamakura City, Kanagawa Prefecture, Japan, and the total number of users was 61. Based on the results of the web questionnaire survey, the usefulness of the system when sightseeing was high, and the recommendation function of sightseeing spots, which is an original function, received mainly good ratings. From the results of the access analysis of users’ log data, the total number of sessions in this system was 329, 77% used mobile devices, and smartphones were used most frequently. Therefore, it is evident that the system was used by different types of devices just as it was designed for, and that the system was used according to the purpose of the present study, which is to support the sightseeing activities of users.

Construction and demonstration experiment of similar spot recommendation system based on emotion word contained in word-of-mouth information

Construction and demonstration experiment of similar spot recommendation system based on emotion word contained in word-of-mouth information

A Sightseeing Spot Recommendation System That Takes into Account the Change in Circumstances of Users

The present study aimed to design, develop, operate and evaluate a sightseeing spot recommendation system for urban sightseeing spots in order to support individual, as well as group sightseeing activities while taking into consideration the user’s needs, which can change according to the circumstances (each user’s important conditions and sightseeing unit). The system was developed by integrating Web-GIS (Geographic Information Systems), the pairing system, the evaluation system, as well as the recommendation system into a single system, and it was also connected with external SNS (Social Networking Services: Twitter and Facebook). Additionally, the system was operated for four weeks in the central part of Yokohama City in Kanagawa Prefecture, Japan, and the total number of users was 52. Based on the results of the web questionnaire survey, the usefulness of the system when sightseeing was high, and the recommendation function of sightseeing spots, which is an original function, has received mainly good ratings. From the results of the access analysis of users’ log data, it is evident that the system has been used by different types of devices, just as it was designed for, and that the system has been used according to the purpose of the present study, which is to support the sightseeing activities of users.

Evolving recommendations from past travel sequences using soft computing techniques

The World Wide Web (WWW) and mobile devices have become an indispensable part of life in this time. The pervasiveness of location acquisition technologies like global positioning system (GPS) has enabled the convenient logging of the movement sequences of users using mobile devices. This work proposes a personalised tourist spot recommender system for mobile users using genetic algorithm (GA) for a situation when explicit user ratings for tourist spots are not available. Implicit ratings of users for tourist spots are mined using GPS trajectory logs. GA is used to evolve ratings of unvisited spots using implicit ratings. GPS trajectory dataset of 178 users collected by Microsoft Research Asia's GeoLife project is used for the purpose of evaluation and experiments. We emphasise that proposed approach is comparable with existing related approaches when compared in terms of average root mean squared error (RMSE) and provides focused, personalised and relevant recommendations.

Evolving recommendations from past travel sequences using soft computing techniques

The World Wide Web (WWW) and mobile devices have become an indispensable part of life in this time. The pervasiveness of location acquisition technologies like global positioning system (GPS) has enabled the convenient logging of the movement sequences of users using mobile devices. This work proposes a personalised tourist spot recommender system for mobile users using genetic algorithm (GA) for a situation when explicit user ratings for tourist spots are not available. Implicit ratings of users for tourist spots are mined using GPS trajectory logs. GA is used to evolve ratings of unvisited spots using implicit ratings. GPS trajectory dataset of 178 users collected by Microsoft Research Asia's GeoLife project is used for the purpose of evaluation and experiments. We emphasise that proposed approach is comparable with existing related approaches when compared in terms of average root mean squared error (RMSE) and provides focused, personalised and relevant recommendations.

Ubiquitous Crowdsourcing Model for Fuzzy Information Enrichment of Tourist Spot Recommender System

The proposed research aims to integrate contextual information with tourist spot recommender system. Ubiquitous crowdsourcing model has been used for collecting the contextual information using fuzzy linguistic values in current time. The existing tourist spot recommender systems give list tourist spots along with their ratings. Proposed model takes this list as an input and the current fuzzy contextual information collected from crowd present at the spot and computes a new score for each spot/location. This new score not only conveys the popularity of a spot in vicinity but also advices whether this spot is worth visiting at given point in time. A prototype system has been implemented using java and MATLAB and is evaluated by 104 real users.

Ubiquitous crowdsourcing model for fuzzy information enrichment of tourist spot recommender system

The proposed research aims to integrate contextual information with tourist spot recommender system. Ubiquitous crowdsourcing model has been used for collecting the contextual information using fuzzy linguistic values in current time. The existing tourist spot recommender systems give list tourist spots along with their ratings. Proposed model takes this list as an input and the current fuzzy contextual information collected from crowd present at the spot and computes a new score for each spot/location. This new score not only conveys the popularity of a spot in vicinity but also advices whether this spot is worth visiting at given point in time. A prototype system has been implemented using java and MATLAB and is evaluated by 104 real users.