Smart, hybrid and context-aware POI mobile recommender system in tourism in Oman

Abstract

PurposeThe purpose of this study is to identify the knowledge gap and future opportunities for developing mobile recommender system in tourism sector that lead to comfortable, targeted and attractive tourism. A recommender system improves the traditional classification algorithms and has incorporated many advanced machine learning algorithms.Design/methodology/approachDesign of this application followed a smart, hybrid and context-aware recommender system, which includes various recommender systems. With the recommender system's help, useful management for time and budget is obtained for tourists, since they usually have financial and time constraints for selecting the point of interests (POIs) and so more purposeful trip planned with decreased traffic and air pollution.FindingsThe finding of this research showed that the inclusion of additional information about the item, user, circumstances, objects or conditions and the environment could significantly impact recommendation quality and information and communications technology has become one part of the tourism value chain.Practical implicationsThe application consists of (1) registration: with/without social media accounts, (2) user information: country, gender, age and his/her specific interests, (3) context data: available time, alert, price, spend time, weather, location, transportation.Social implicationsThe study’s social implications include connecting the app and registration through social media to a more social relationship, with its textual reviews, or user review as user-generated content for increasing accuracy.Originality/valueThe originality of this research work lies on introducing a new content- and knowledge-based algorithm for POI recommendations. An “Alert” context emphasizing on safety, supplies and essential infrastructure is considered as a novel context for this application.

An Ensemble and Filtering-Based System for Predicting Educational Data Mining

“…In order to create equal-sized training sets, each fold is split into two halves, which are then divided again. Gams [16] primarily depended on this strategy, which they further improved, in order to generate neural network ensembles [19,20]. To make matters even better, Domingos [17] employed cross-validation to speed up the development of his proposed rule induction system, known as RISE [21].…”

“…The execution of a graded learning algorithm, according to Afsahhosseini and Al-Mulla [16], categorizes instances at the meta-level by using the meta classifier as a classification criteria, which is a classification criterion for the meta classifier [23]. The primary rationale behind the grading is that it teaches the meta classifier to categorize specific bases in order to forecast the instance whenever the base classifier fails in a particular job, which is the goal of the grading.…”

“…The ensemble technique is advantageous because it gives the much-needed incentive for improving the prediction accuracy of several classifiers after the aggregated outputs have been created, and this is because Although the data is complicated, ensembles have the capacity to achieve higher accuracy and, as a result, to avoid overfitting of individual classifiers and generalization mistakes in the classification process. Several research papers have proven that employing the ensemble strategy to combine the outputs of separate classifiers resulted in a decrease in generalization error [14][15][16].…”