A novel recommendation approach based on chronological cohesive units in content consuming logs
Introduction
Recommender systems are one of the subclasses of information filtering systems that seek to recommend content for users [12], [37]. Today, due to the huge amount of available data and the development of effective data processing algorithms, recommender systems have become indispensable tools in various domains, such as movies, books, news, music, and so on [6], [7], [19], [20], [35], [38], [44], [45]. Indeed, recommender systems have a particularly significant effect on content businesses. As examples, over a decade ago, two thirds of movie rentals are prompted by recommendations in the case of Netflix. More than 38% of click-throughs on Google news are generated by recommendations, and 35% of sales on Amazon are attributable to recommendations [5].
Most of recommender systems are based on content consuming logs of users which are sequences of the content consumed by users. In a sequential log, neighboring items are associated each other, but all the neighboring items are not equally associated. The example in Fig. 1 shows two web navigational logs of two users. The users visited the same pages, but the orders of the visits differ. User A first visited three camera pages and then three smartphone pages, while user B navigated camera pages and smartphone pages in a mixed order.
Since the two users have visited the same pages, we may recommend the same pages to the both users if we do not consider the orders. However, the interests of user A seem to have changed from cameras to smartphones, while user B’s interests remain with photo-taking devices. That is, the log of user A can be separated into two sub-sequences in which items are more strongly associated. It will be helpful for user A to recommend web pages on smartphones considering the recent three pages on smartphones, but for user B web pages on photo-taking devices considering all the six pages. If we are able to separate user logs into cohesive sub-sequences which reflect consuming context, such as interest, we can obtain richer information and provide better recommendations for users.
In this paper, we are focusing on the cohesive sub-sequences in sequential logs. Because users consume content within contexts, it is very probable that there are sub-sequences in which contents are strongly associated. The identification of those cohesive sub-sequences facilitates the recommendation of next content to users.
Existing recommendation approaches for sequential logs can be categorized into transaction-based [11], [14], [15], [20], [25], [29], [34], [39], [41], [42], [43], sequence-based [8], [21], [26], session segmentation-based [9], [27], [30], [33] and time-aware recommendations [3], [4], [10], [31]. Transaction-based approaches consider content consuming logs as sets rather than sequences, so that it cannot aware the cohesive sub-sequences which reflect users’ consuming context. On the other hand, sequence-based approaches may generate different recommendation models depending on the orders of consumptions. However, emphasis on modeling consumption orders may generate overfitted and complex models [2], thus the performance of recommendation could be degraded. Session segmentation-based approaches try to separate user logs into sessions to identify items strongly associated each other. However, most approaches relied on expert knowledge to identify sessions. Time-aware approaches generate recommendation lists by predicting temporal behaviors of users. It can recommend novel items, but the model complexity could be high.
The existing methods were unrecognized or limited to considering cohesive subsequences in user logs to recommend items to users. In this paper, we splits content consuming logs into cohesive sub-sequences or chronological cohesive units (CCUs), in which contents have strong associations with each other. It analyzes the CCUs to find strongly associated items and recommends items that have strong associations with the current CCU. Because content consuming logs are split into cohesive units, the associations found in the units are much stronger than the associations found in the original non-split content consuming logs. Thus, we can expect an improvement of the recommendation performance.
The question is how to split the content consuming logs of users into cohesive units. We assume that any cohesiveness in the logs mainly originates from the context in which users consume content. So, we first select various features which may reflect the contexts of content consuming [16]. We combine the features to establish splitting rules using a genetic programming approach. After splitting, we find strongly associated content sets in CCUs and recommend next content based on an association rule-based approach. The association rule-based method is suitable for recommending next content by observing previously consumed content [25].
To implement this approach, it is hard to find out the optimal parameters such as support, confidence values for association rules, and the number of pre-consumed content for recommendations. In this paper, the parameters for association rules are also found by a genetic approach, and the number of pre-consumed content for recommendations is also dynamically determined based on CCUs.
The proposed approach is evaluated using two-real datasets: web page navigation logs and movie consuming logs which have totally different characteristics. The experiments show that our approach is superior to the existing recommendation models in the aspects of hit ratio, click-soon ratio, sparsity, diversity and serendipity.
The rest of the paper is organized as follows. Section 2 presents an overview of related work. Section 3 describes the proposed approach. We present the experiments in Section 4 and conclude in Section 5.
Section snippets
Related work
The recommendation approach developed in this paper is concerned with sequential content consuming logs. In this section, transaction-based recommendation, sequence-based recommendation, session segmentation-based recommendation and time-aware recommendation approaches are discussed.
The proposed approach
In this section, we propose a novel recommendation approach based on chronological cohesive units which contain strongly associated contents. This section consists of four subsections: feature development, splitting content consuming logs, recommendation based on CCUs and genetic optimization. The overview of the proposed approach is shown in Fig. 2.
Our approach first splits content consuming logs into cohesive sub-sequences by a decision tree optimized by a genetic programming approach. Then,
Experiments
This section consists of three subsections: datasets and baselines, performance evaluation and recommendation analysis. In the first subsection, we present the details of the datasets and the baselines. In the performance evaluation subsection, we present performance evaluations with web navigational logs and movie consuming logs. The performances are evaluated with the hit ratio and the click-soon ratio, and compared with six baselines [9], [27], [30], [39], [45]. In the recommendation
Conclusion
In this paper, we proposed a novel recommendation approach based on chronological cohesive units in content consuming logs. Unlike the existing methods, the proposed method split the users’ past contents consumption records into highly cohesive units (called chronological cohesive units, CCUs), made association rules based on CCUs, and recommended contents.
We evaluated the proposed method using two types of real-world datasets (web and movie logs) which have totally different characteristics.
Acknowledgment
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2016R1A2B4015820) and also supported by Ministry of Culture, Sports and Tourism (MCST) and Korea Creative Content Agency (KOCCA) in the Culture Technology (CT) Research & Development Program 2016 (No. S-2016-0882-000).
Jaekwang Kim was born in Seoul, Republic of Korea in 1980. He received BS, MS and PhD degrees from Sungkyunkwan University at Suwon, Republic of Korea in 2004, and 2006, respectively. His research interests include networks, security, and intelligent systems. He received the best presentation paper award at ICUIMC, Suwon, Korea in Jan. 2009, and was elected as a bronze medal superior student in the Sungkyunkwan University Brain Korea 21 enterprise department. He is a currently researcher at the
References (46)
- et al.
An investigation on the serendipity problem in recommender systems
Inf. Process. Manag.
(2015) - et al.
Recommender system based on click stream data using association rule mining
Expert Syst. Appl.
(2011) - et al.
A survey of serendipity in recommender systems
Knowl.-Based Syst.
(2016) - et al.
The BellKor 2008 Solution to the Netflix Prize
(2008) - et al.
Modeling user consumption sequences
- et al.
Time-aware evaluation of methods for identifying active household members in recommender systems
- et al.
Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols
User Model. User-Adapt. Interact.
(2014) - et al.
Tutorial on Music Recommendation
(2007) - et al.
Application of artificial immune systems combines collaborative filtering in movie recommendation system
- et al.
Improved neighborhood search for collaborative filtering
Int. J. Fuzzy Log. Intell. Syst.
(2018)
Selective Markov models for predicting Web page accesses
ACM Trans. Internet Technol. (TIOT)
Improving music recommendation in session-based collaborative filtering by using temporal context
Time-sensitive recommendation from recurrent user activities
Profit estimation error analysis in recommender systems based on association rules
Recommender system based on random walk with topic model
Prediction of customers' needs: an approach based on similarity search in transactions databases
Recommending music based on probabilistic latent semantic analysis on Korean radio episodes
5W1H: Unified user-centric context
Diversity, serendipity, novelty, and coverage: a survey and empirical analysis of beyond-accuracy objectives in recommender systems
ACM Trans. Int. Intel. Sys. (TIIS)
A clickstream-based collaborative filtering personalization model: towards a better performance
An approach for music recommendation using content-based analysis and collaborative filtering
Int. J. Inf.
An approach to extract informative rules for Web page recommendation by genetic programming
IEICE Trans. Comm. E95.B
A music recommendation system based on personal preference analysis
Cited by (6)
Is UGC sentiment helpful for recommendation? An application of sentiment-based recommendation model
2024, Industrial Management and Data SystemsMerchant Recommender System Using Credit Card Payment Data
2023, Electronics (Switzerland)A Multi-Dimensional Source Selection Based on Topic Modelling
2022, Journal of Information Science and EngineeringGeneralizing and Processing Topological Data using Sentence Data Structure
2021, Proceedings of the 2021 15th International Conference on Ubiquitous Information Management and Communication, IMCOM 2021Switching strategy of recommendation algorithms in online dating platform
2019, Proceedings - 2019 7th International Conference on Advanced Cloud and Big Data, CBD 2019
Jaekwang Kim was born in Seoul, Republic of Korea in 1980. He received BS, MS and PhD degrees from Sungkyunkwan University at Suwon, Republic of Korea in 2004, and 2006, respectively. His research interests include networks, security, and intelligent systems. He received the best presentation paper award at ICUIMC, Suwon, Korea in Jan. 2009, and was elected as a bronze medal superior student in the Sungkyunkwan University Brain Korea 21 enterprise department. He is a currently researcher at the SKKU Convergence Institute for Intelligence and Informatics.
Jee-Hyong Lee received MS and PhD degrees in computer science from Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea, in 1995 and 1999, respectively. He was an international fellow at SRI International, California from 2000 to 2001. He has been working as a faculty at Sungkyunkwan University, Suwon, Korea since March 2002. His current interest fields are recommender systems, machine learning, and intelligent information processing.