When Recommending TV Content, Context is Critical Dataset and Algorithms PROJECT TITLE : The Importance of Context When Recommending TV Content Dataset and Algorithms ABSTRACT: Home entertainment systems are used in a variety of settings with one or more concurrent users, with the complexity of selecting media to consume increasing quickly over the previous decade. Contextual settings influence users' decision-making processes, yet data to help the creation and evaluation of context-aware recommender systems is sparse. We present a dataset of self-reported TV usage that includes contextual information about watching conditions in this research. We show how genre preference affects, among other things, the number of current users and their attention levels. We then compare the results to contextless predictions by evaluating the performance of predicting specific genres given various configurations of contextual information. The findings reveal that adding contextual characteristics in the prediction leads to significant gains, with both temporal and social context playing a role. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Deep Neural Networks for Robust Lane Detection in Continuous Driving Scenes Semi-supervised classification is used to recognise traffic signs by combining global and local features.