Austin R. Benson
ABSTRACT
We study sequences of consumption in which the same item may be consumed multiple times. We identify two macroscopic behavior patterns of repeated consumptions. First, in a given user's lifetime, very few items live for a long time. Second, the last consumptions of an item exhibit growing inter-arrival gaps consistent with the notion of increasing boredom leading up to eventual abandonment.
We then present what is to our knowledge the first holistic model of sequential repeated consumption, covering all observed aspects of this behavior. Our simple and purely combinatorial model includes no planted notion of lifetime distributions or user boredom; nonetheless, the model correctly predicts both of these phenomena. Further, we provide theoretical analysis of the behavior of the model confirming these phenomena. Additionally, the model quantitatively matches a number of microscopic phenomena across a broad range of datasets.
Intriguingly, these findings suggest that the observation in a variety of domains of increasing user boredom leading to abandonment may be explained simply by probabilistic conditioning on an extinction event in a simple model, without resort to explanations based on complex human dynamics.
- E. Adar, J. Teevan, and S. T. Dumais. Large scale analysis of Web revisitation patterns. In CHI, pages 1197--1206, 2008. Google Scholar
Digital Library
- E. Adar, J. Teevan, and S. T. Dumais. Resonance on the Web: Web dynamics and revisitation patterns. In CHI, pages 1381--1390, 2009. Google ScholarDigital Library
- G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. TKDE, 17(6):734--749, 2005. Google ScholarDigital Library
- A. Anderson, R. Kumar, A. Tomkins, and S. Vassilvitskii. The dynamics of repeat consumption. In WWW, pages 419--430, 2014. Google ScholarDigital Library
- J. Bobadilla, F. Ortega, A. Hernando, and A. Gutiérrez. Recommender systems survey. Knowledge-Based Systems, 46:109--132, 2013. Google ScholarDigital Library
- Ò. Celma Herrada. Music Recommendation and Discovery in the Long Tail. PhD thesis, Universitat Pompeu Fabra, 2009.Google Scholar
- J. Chen, C. Wang, and J. Wang. Will you "reconsume" the near past? Fast prediction on short-term reconsumption behaviors. In AAAI, pages 23--29, 2015. Google ScholarDigital Library
- E. H. Chi, P. Pirolli, K. Chen, and J. Pitkow. Using information scent to model user information needs and actions and the Web. In CHI, pages 490--497, 2001. Google ScholarDigital Library
- C.-M. Chiu, M.-H. Hsu, H. Lai, and C.-M. Chang. Re-examining the influence of trust on online repeat purchase intention: The moderating role of habit and its antecedents. Decision Support Systems, 53(4):835--845, 2012. Google ScholarDigital Library
- E. Cho, S. A. Myers, and J. Leskovec. Friendship and mobility: User movement in location-based social networks. In KDD, pages 1082--1090, 2011. Google ScholarDigital Library
- A. Clauset, C. R. Shalizi, and M. E. Newman. Power-law distributions in empirical data. SIAM review, 51(4):661--703, 2009. Google ScholarDigital Library
- J. D. Cohen, S. M. McClure, and J. Y. Angela. Should I stay or should I go? how the human brain manages the trade-off between exploitation and exploration. Philosophical Transactions of the Royal Society B: Biological Sciences, 362(1481):933--942, 2007. Google ScholarCross Ref
- A. Das Sarma, S. Gollapudi, R. Panigrahy, and L. Zhang. Understanding cyclic trends in social choices. In WSDM, pages 593--602, 2012. Google ScholarDigital Library
- D. Downey, S. Dumais, D. Liebling, and E. Horvitz. Understanding the relationship between searchers' queries and information goals. In CIKM, pages 449--458, 2008. Google ScholarDigital Library
- G. Dror, D. Pelleg, O. Rokhlenko, and I. Szpektor. Churn prediction in new users of Yahoo! answers. In WWW, pages 829--834, 2012. Google ScholarDigital Library
- J. Jacoby and D. B. Kyner. Brand loyalty vs. repeat purchasing behavior. Journal of Marketing Research, pages 1--9, 1973. Google ScholarCross Ref
- B. E. Kahn, M. U. Kalwani, and D. G. Morrison. Measuring variety-seeking and reinforcement behaviors using panel data. Journal of Marketing Research, pages 89--100, 1986. Google ScholarCross Ref
- K. Kapoor, K. Subbian, J. Srivastava, and P. Schrater. Just in time recommendations: Modeling the dynamics of boredom in activity streams. In WSDM, pages 233--242, 2015. Google ScholarDigital Library
- K. Kapoor, M. Sun, J. Srivastava, and T. Ye. A hazard based approach to user return time prediction. In KDD, pages 1719--1728, 2014. Google ScholarDigital Library
- M. Karnstedt, T. Hennessy, J. Chan, and C. Hayes. Churn in social networks: A discussion boards case study. In SocialCom, pages 233--240, 2010. Google ScholarDigital Library
- J. G. March. Exploration and exploitation in organizational learning. Organization Science, 2(1):71--87, 1991. Google ScholarDigital Library
- L. McAlister. A dynamic attribute satiation model of variety-seeking behavior. Journal of Consumer Research, pages 141--150, 1982. Google ScholarCross Ref
- C. Mitchell, M. Harper, and L. Jamieson. On the complexity of explicit duration HMM's. IEEE Transactions on Speech and Audio Processing, 3(3):213--217, 1995. Google ScholarCross Ref
- M. Mitzenmacher. A brief history of generative models for power law and lognormal distributions. Internet Mathematics, 1(2):226--251, 2004. Google ScholarCross Ref
- M. Mitzenmacher. Dynamic models for file sizes and double Pareto distributions. Internet Mathematics, 1(3):305--333, 2004. Google ScholarCross Ref
- L. Page, S. Brin, R. Motwani, and T. Winograd. The PageRank citation ranking: Bringing order to the Web. Technical report, InfoLab, Stanford University, 1999.Google Scholar
- F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. Scikit-learn: Machine learning in Python. JMLR, 12:2825--2830, 2011. Google ScholarDigital Library
- R. K. Ratner, B. E. Kahn, and D. Kahneman. Choosing less-preferred experiences for the sake of variety. Journal of Consumer Research, 26(1):1--15, 1999. Google ScholarCross Ref
- W. J. Reed and M. Jorgensen. The double Pareto-lognormal distribution--a new parametric model for size distributions. Communications in Statistics-Theory and Methods, 33(8):1733--1753, 2004. Google ScholarCross Ref
- K. H. Schlag. Why imitate, and if so, how?: A boundedly rational approach to multi-armed bandits. JET, 78(1):130--156, 1998. Google ScholarCross Ref
- J. Teevan, E. Adar, R. Jones, and M. Potts. History repeats itself: Repeat queries in Yahoo's logs. In SIGIR, pages 703--704, 2006. Google ScholarDigital Library
- J. Teevan, E. Adar, R. Jones, and M. A. Potts. Information re-retrieval: Repeat queries in Yahoo's logs. In SIGIR, pages 151--158, 2007. Google ScholarDigital Library
- R. West, A. Paranjape, and J. Leskovec. Mining missing hyperlinks from human navigation traces: A case study of Wikipedia. In WWW, pages 1242--1252, 2015. Google ScholarDigital Library
- R. West, J. Pineau, and D. Precup. Wikispeedia: An online game for inferring semantic distances between concepts. In IJCAI, pages 1598--1603, 2009. Google ScholarDigital Library
- J. Yang, X. Wei, M. S. Ackerman, and L. A. Adamic. Activity lifespan: An analysis of user survival patterns in online knowledge sharing communities. In ICWSM, 2010.Google Scholar
Index Terms
- Modeling User Consumption Sequences
Recommendations
Modeling Item-Specific Temporal Dynamics of Repeat Consumption for Recommender Systems
WWW '19: The World Wide Web ConferenceRepeat consumption is a common scenario in daily life, such as repurchasing items and revisiting websites, and is a critical factor to be taken into consideration for recommender systems. Temporal dynamics play important roles in modeling repeat ...
The dynamics of repeat consumption
WWW '14: Proceedings of the 23rd international conference on World wide webWe study the patterns by which a user consumes the same item repeatedly over time, in a wide variety domains ranging from check-ins at the same business location to re-watches of the same video. We find that recency of consumption is the strongest ...
The role of metacognitions in problematic Internet use
Research has suggested that negative emotions are associated with problematic Internet use. This study investigated the role of metacognitions as a mediator of the relationship between negative emotions and problematic Internet use. A sample of 97 ...
Comments