Probabilistic latent semantic indexing
Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
Maximizing the spread of influence through a social network
Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Information diffusion through blogspace
Proceedings of the 13th international conference on World Wide Web
IEEE Transactions on Knowledge and Data Engineering
Nonsmooth Nonnegative Matrix Factorization (nsNMF)
IEEE Transactions on Pattern Analysis and Machine Intelligence
Personalized recommendation driven by information flow
SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
Extracting influential nodes for information diffusion on a social network
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Personalized recommendation based on the personal innovator degree
Proceedings of the third ACM conference on Recommender systems
Learning influence probabilities in social networks
Proceedings of the third ACM international conference on Web search and data mining
Discovering latent influence in online social activities via shared cascade poisson processes
Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
Hi-index | 0.00 |
This paper presents a probabilistic influence model for smartphone usage; it applies a latent group model to social influence. The probabilistic model is built on the assumption that a time series of students' application downloads and activations can be represented by individual inter-personal influence factors which consist of latent groups. To verify that model with its assumption, about 160 university students voluntarily participated in a mobile application usage monitoring experiment. Analysis could identify latent user groups by observing predictive performance against reduced dimensions of factor matrices with NMF. Proper dimension reduction is shown to significantly improve predictive performance, which implies a reduction in the over-fitting phenomenon. With this improvement, the model outperforms conventional collaborative filtering models and popularity models in perplexity evaluation. The results validate the model and its assumption as well as its usefulness.