A recommender system based on implicit feedback for selective dissemination of ebooks

Abstract

In this study, we describe a recommendation system for electronic books. The approach is based on implicit feedback derived from user's interaction with electronic content. User's behavior is tracked through several indicators that are subsequently used to feed the recommendation engine. This component then provides an explicit rating for the material interacted with. The role of this engine could be modeled as a regression task where content is rated according to the mentioned indicators. In this context, we benchmark twelve popular machine learning algorithms to perform this final function and evaluate the quality of the output provided by the system.

Recommendation and Classification Systems: A Systematic Mapping Study

“…e search engines returned multiple results (Table 4), with a total of 21 proposals remaining were potential candidates. A smart-device news recommendation technology based on the user click behavior [44] Recommendation as link prediction in bipartite graphs: A graph kernel-based machine learning approach [45] A novel approach towards context based recommendations using support vector machine methodology [46] A smartphone-based activity-aware system for music streaming recommendation [47] An app usage recommender system: improving prediction accuracy for both warm and cold start users [48] Proposing design recommendations for an intelligent recommender system logging stress [49] A recommender system based on implicit feedback for selective dissemination of eBooks [50] A novel recommender system based on FFT with machine learning for predicting and identifying heart diseases [51] An approach to content based recommender systems using decision list based classification with k-DNF rule set [52] Probabilistic approach for QoS-aware recommender system for trustworthy web service selection [53] Approach to cold-start problem in recommender systems in the context of web-based education [54] Context and intention-awareness in POIs recommender systems [55] A collaborative filtering-based re-ranking strategy for search in digital libraries [56] Learning users' interests by quality classification in market-based recommender systems [57] Mobile content recommendation system for revisiting user using content-based filtering and clientside user profile [58] A hybrid collaborative filtering algorithm based on KNN and gradient boosting [59] A scalable collaborative filtering algorithm based on localized preference [60] Recommended or not recommended? Review classification through opinion extraction [61] Meta-feature based data mining service selection and recommendation using machine learning models [62] Personalized channel recommendation deep learning from a switch sequence [63] Affective labeling in a content-based recommender system for images [64] A novel approach towards context sensitive recommendations based on machine learning methodology [65] A distance-based approach for action recommendation [66] Ranking and classifying attractiveness of photos in folksonomies…”

A Nondisturbing Service to Automatically Customize Notification Sending Using Implicit-Feedback

“…Fortunately, there are abundant implicit data that may serve to model the user preferences. In fact, there are authors that target the problem where only implicitfeedback is provided [23,24]. Núñez-Valdez et al [24] propose a system that converts implicit behavioral data into explicit-feedback to recommend books.…”

“…In fact, there are authors that target the problem where only implicitfeedback is provided [23,24]. Núñez-Valdez et al [24] propose a system that converts implicit behavioral data into explicit-feedback to recommend books. Typical user actions are considered, such as highlighting content, adding notes, or suggesting content to other contacts.…”

Framework for Hybrid Book Recommender System based on Opinion Mining

“…Polarity of user comments is calculated using Naïve Bayes Text Classifier and product rating is also used to score the products and list of best products is generated for recommendation. Edward Rolando Nunez-Valdez et al [11] Author tried to focus on defining a mathematical model that allowed us to develop an algorithm for converting implicit into explicit feedback in an e-book platform. Nine implicit actions were evaluated as positive by twelve popular machine learning algorithm Tamara Alvarez-Lopez et al [12] In this paper new schemas are proposed that were useful for improving the quality of book recommendation by extracting the most important aspect expressed along with associated sentiment in reviews by experts and informal ones .…”