AIMED- A Personalized TV Recommendation System

Abstract

Abstract. Previous personalized DTV recommendation systems focus only on viewers' historical viewing records or demographic data. This study proposes a new recommending mechanism from a user oriented perspective. The recommending mechanism is based on user properties such as Activities, Interests, Moods, Experiences, and Demographic information-AIMED. The AIMED data is fed into a neural network model to predict TV viewers' program preferences. Evaluation results indicate that the AIMED model significantly increases recommendation accuracy and decreases prediction errors compared to the conventional model.

Tuning metadata for better movie content-based recommendation systems

“…A more sophisticated approach has been considered in [21], where not only historical information (e.g. ratings or gender preferences) is used but also information that can change in each access to the system (e.g.…”

A cloud-based intelligent TV program recommendation system

“…Viewer activity, interest, emotions, experiences, and statistic information have been used to build a recommendation system [3] that lowers the barrier of usage for new users [4], and personalizes the recommendation service [5]. A system that allows users to build their own semantic web has been developed [6].…”

Evolving temporal association rules in recommender system

“…In content-based approaches, items are recommended based on items previously preferred by a specific user [24]. For example, as a special case of content-based systems, knowledge-based recommender systems directly compute users' favourite items based on their historic profile [11]. The computational intelligence methods apply intelligence techniques to construct proper recommendation models, including artificial neural networks [30], clustering techniques [9,31], evolutionary algorithms [17,28] and fuzzy set techniques [18].…”

“…Therefore, only the right in time recommendations are truly valuable. However, a number of studies in traditional recommender systems focus on the problem of which item to recommend [1,9,11,24], while relatively few studies also consider the best time to recommend an item.…”