A Software Popularity Recommendation Method Based on Evaluation Model

Wang, Yan; Bai, Peixiang; Yang, Deyu; Zhou, Jian-Tao; Song, Xiaoyu

doi:10.1109/compsac.2018.00070

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our study, we challenge the definition and evaluation of the mainstream popularity baseline, which is non-personalized. Software popularity algorithm based on evaluation model [18] is a non-personalized method to recommend popular softwares to users. In the computation of popularity, time duration since an item's release date is applied as a shrinkage factor to popularity.…”

Section: Related Workmentioning

confidence: 99%

A Re-visit of the Popularity Baseline in Recommender Systems

Sun

Zhang

et al. 2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Popularity is often included in experimental evaluation to provide a reference performance for a recommendation task. To understand how popularity baseline is defined and evaluated, we sample 12 papers from top-tier conferences including KDD, WWW, SIGIR, and RecSys, and 6 open source toolkits. We note that the widely adopted MostPop baseline simply ranks items based on the number of interactions in the training data. We argue that the current evaluation of popularity (i) does not reflect the popular items at the time when a user interacts with the system, and (ii) may recommend items released after a user's last interaction with the system. On the widely used MovieLens dataset, we show that the performance of popularity could be significantly improved by 70% or more, if we consider the popular items at the time point when a user interacts with the system. We further show that, on MovieLens dataset, the users having lower tendencies on movies tend to follow the crowd and rate more popular movies. Movie lovers who rate a large number of movies, rate movies based on their own preferences and interests. Through this study, we call for a re-visit of the popularity baseline in recommender system to better reflect its effectiveness.

show abstract

Section: Related Workmentioning

confidence: 99%

A Re-visit of the Popularity Baseline in Recommender Systems

Sun

Zhang

et al. 2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…Besides, NLC is developed initially to explain the waning phenomena in heat transfer mechanisms between an object and its environment [34]. As a foundational physical law, it has found relevance in the decaying processes of social media popularity [35] and the diminishing impact of monetary policy [36]. It's also incorporated into optimization algorithms [37] as a possible decreasing mechanism.…”

Section: Introductionmentioning

confidence: 99%

Quantifying the Waning Effect of Non-pharmaceutical Interventions with Case Study in COVID-19

Cao,

Jin

2024

Preprint

View full text Add to dashboard Cite

The multiple pandemics of illnesses like COVID-19 over human history have caused significant threats to public health. To combat such pandemics, stringent control measures, including non-pharmaceutical interventions (NPIs), play a critical role, while their waning effect on containing infectious diseases still requires quantitative and explainable research. Most NPI-related studies represent NPI effect by a steady value or a probability distribution, which often regard the impact of NPI as a fixed process. In reality, the effectiveness of NPI is time-varying and influenced by external factors. An increasing number of studies recognize the phenomenon of NPI's waning effect. To mathematically depict the decreasing process of the NPI effect, an innovative pandemic model called SVEIC-NLC is proposed, taking into account the changing nature of NPI effect. The diminishing effectiveness of NPIs is characterized by a physical law called Newton's Law of Cooling (NLC), representing the first attempt at applying NLC to epidemics. To validate SVEIC-NLC, we conduct experiments using COVID-19 as a case study in Germany, Greece, and the Philippines. The experiments illustrate that the effectiveness of NPI decays over time. Further, SVEIC-NLC is compared with six other cutting-edge methods in predicting cases for three states in the US. These show the necessity of evaluating and incorporating the waning effect of NPI in reasonably preparing a control strategy and containing a disease.

show abstract