RecTime: Real-Time recommender system for online broadcasting

Park, Yoojin; Oh, Jinoh; Yu, Hwanjo

doi:10.1016/j.ins.2017.04.038

Cited by 36 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of these systems disregarded users' time context and time-dependent watching patterns. As users' time context is an important factor for TV watching, other TV recommender systems use time context as input, which is a time-aware system [13][14][15][16][17][18][19][20][21]. In this section, these two types of TV recommender systems are surveyed.…”

Section: Related Workmentioning

confidence: 99%

“…In recent years, TV recommender systems considering time-aware consumption patterns have been actively researched [13][14][15][16][17][18][19][20][21]. For example, Oh et al proposed a time-dependent user profiling technique that splits a user's watching logs into certain time slots and re-merges consecutive time slots by using a hierarchical clustering method [13].…”

Section: Time-aware Tv Recommender Systemsmentioning

confidence: 99%

“…They developed user preferences considering broadcasting times and staying times. Then, a 4-D factor factorization is applied [21].…”

Section: Time-aware Tv Recommender Systemsmentioning

confidence: 99%

See 2 more Smart Citations

A Television Recommender System Learning a User’s Time-Aware Watching Patterns Using Quadratic Programming

Kim

Lee

2018

Applied Sciences

View full text Add to dashboard Cite

In this paper, a novel television (TV) program recommendation method is proposed by merging multiple preferences. We use channels and genres of programs, which is available information in standalone TVs, as features for the recommendation. The proposed method performs multi-time contextual profiling and constructs multiple-time contextual preference matrices of channels and genres. Since multiple preference models are constructed with different time contexts, there can be conflicts among them. In order to effectively merge the preferences with the minimum number of conflicts, we develop a quadratic programming model. The optimization problem is formulated with a minimum number of constraints so that the optimization process is scalable and fast even in a standalone TV with low computational power. Experiments with a real-world dataset prove that the proposed method is more efficient and accurate than other TV recommendation methods. Our method improves recommendation performance by 5-50% compared to the baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Time-aware Tv Recommender Systemsmentioning

confidence: 99%

See 1 more Smart Citation

A Television Recommender System Learning a User’s Time-Aware Watching Patterns Using Quadratic Programming

Kim

Lee

2018

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Recently, hybrid models are proposed in existing studies to deal with online process, for example, [23] captures user's changing preferences over the broadcasting time of TV shows as staying preferences at each interval of the broadcasting. For example, a study [35] of the development of vocabulary for capturing a customer's affective experiences to apparel under design has been proposed.…”

Section: Challenges and Literature Reviewmentioning

confidence: 99%

Evolving temporal association rules in recommender system

Zhou

Hirasawa²

2017

Neural Comput & Applic

View full text Add to dashboard Cite

This research involves implementation of genetic network programming (GNP) and ant colony optimization (ACO) to solve the sequential rule mining problem for commercial recommendations in time-related transaction databases. Excellent recommender systems should be capable of detecting the customers' preference in a proactive and efficient manner, which requires exploring customers' potential needs with an accurate and timely approach. Due to the changing nature of customers' preferences and the differences with the traditional find-allthen-prune approach, the interesting temporal association rules are extracted by the metaheuristics, genetic algorithms-based method of GNP. Additionally, a useful model is constructed using the obtained rules to forecast future customer needs and an ACO approach to evolve the online recommender system continuously. The methodology is experimentally evaluated in a real-world application by analysing the customer database of an online supermarket.

show abstract

“…As Internet is now a fully integrated part of our society, the use of RSs is becoming increasingly important in a range of areas (Park, Kim, Choi, & Kim, ). For example, RSs play a key role in online stores by highlighting the items that may be more interesting to the user (Sivapalan, Sadeghian, Rahnama, & Madni, ; Wang & Zhang, ), fully personalized online advertising (Bulander, Decker, Schiefer, & Kolmel, ), suggestions on multimedia content (Park, Oh, & Yu, ), content rating sites for tourism, film, research, and many other sectors (Adomavicius & Tuzhilin, ) and in the area on which this work focuses, social networks such as the works published in Lee and Brusilovsky () and in Liu and Aberer (). Because there are many areas to which RSs are applied, multiple mechanisms have also been proposed for the implementation of recommendations.…”

Section: Introductionmentioning

confidence: 99%

Hybrid job offer recommender system in a social network

et al. 2019

View full text Add to dashboard Cite

Recommender systems (RSs) play a very important role in web navigation, ensuring that the users easily find the information they are looking for. Today's social networks contain a large amount of information and it is necessary that they employ a mechanism that will guide users to the information they are interested in. However, to be able to recommend content according to user preferences, it is necessary to analyse their profiles and determine their preferences. The present work proposes a job offer RS for a career‐oriented social network. The recommendation system is a hybrid, it consists of a case‐based reasoning (CBR) system and an argumentation framework, based on a multi‐agent system (MAS) architecture. The CBR system uses a series of metrics and similar cases to decide whether a job offer is likely to be recommended to a user. Besides, the argumentation framework extends the system with an argumentation CBR, through which old and similar cases can be obtained from the CBR system. Finally, a discussion process is established amongst the agents who debate using their experience from past cases to take a final decision.

show abstract

RecTime: Real-Time recommender system for online broadcasting

Cited by 36 publications

References 19 publications

A Television Recommender System Learning a User’s Time-Aware Watching Patterns Using Quadratic Programming

A Television Recommender System Learning a User’s Time-Aware Watching Patterns Using Quadratic Programming

Evolving temporal association rules in recommender system

Hybrid job offer recommender system in a social network

Contact Info

Product

Resources

About