Experiences from Integrating Collaborative Filtering in a Mobile City Guide

Abstract

This chapter presents an approach to extend a real world mobile tourist guide running on personal digital assistants (PDAs) with collaborative filtering. The system builds a model of item similarities based on explicit and implicit ratings. This model is then utilized to generate recommendations in several ways. The approach integrates the current user location as context. Experiences gained in two field studies are reported. In the first one, 30 participants – real tourists visiting Prague – used the recommender function and were asked to fill out a questionnaire with promising results. In a second field study analyzing usage log files, an improvement of recommendations based on the collaborative filter in comparison to the pure location-based filter used before was discovered. In addition, recommendations based on implicit ratings derived from audio playback duration outperformed the model based on explicit ratings.

An Engagement Model Based on User Interest and QoS in Video Streaming Systems

“…This method is accurate but not practical in time-sensitive applications like online VoD systems. Instead, user behaviors, such as the time spent on a page, scrolling and clicks on web pages [36,37], time spent on a video [38,39], and purchases in the past [40], are used as implicit ratings in some applications.…”

“…Based on the collected users' interest in the selected sessions, we next use Matrix Factorization (MF) [33,34], a typical Collaborative Filtering (CF) algorithm [35][36][37][38], to infer their interest in other sessions. Compared with some other typical CF algorithms, e.g., KNN algorithm [35,36], the MF algorithm is better at dealing with the data sparsity [36] and, in our experiments, the data used for training is quite sparse. The selected sessions (used for both training and testing) only account for 23% of the sessions in our dataset.…”

“…To alleviate value 0 in the logarithm operators, all the QoS values are increased by 1; i.e., = ln( + 1), where is the original QoS value and is the logarithmical one. We employ the correlation metrics Pearson correlation coefficient t [36] and Spearman rank coefficient [39]. The first metric could identify the linear relationship with some Gaussian noise while the second one emphasizes the monotonicity between variables.…”