Yashar Moshfeghi

The realisation and the variability of information needs (IN) with respect to a searcher’s gap in knowledge is driven by the perceived Anomalous State of Knowledge (ASK). The concept of Feeling-of-Knowing (FOK), as the introspective feeling of knowledge awareness, shares the characteristics of an ASK state. From an IR perspective, FOK as a premise to trigger IN is unexplored. Motivated by the neuroimaging studies in IR, we investigate the neurophysiological drivers associated with FOK, to provide evidence validating FOK as a distinctive state in IN realisation. We employ Electroencephalography to capture the brain activity of 24 healthy participants performing a textual Question Answering IR scenario. We analyse the evoked neural patterns corresponding to three states of knowledge: i.e., (1)“I know”, (2)“FOK”, (3)“I do not know”. Our findings show the distinct neurophysiological signatures (N1, P2, N400, P6) in response to information segments processed in the context of our three levels. They further reveal that the brain manifestation associated with “FOK” does not significantly differ from the ones associated with “I do not know”, indicating their association with recognition of a gap in knowledge and as such could further inform the IN formation on different levels of knowing.

Collaborative Filtering (CF) recommendation algorithms are a popular solution to the information overload problem, aiding users in the item selection process. Relevant research has long focused on refining and improving these models to produce better (more effective) recommendations, and has converged on a methodology to predict their effectiveness on target datasets by evaluating them on random samples of the latter. However, predicting the efficiency of the solutions—especially with regard to their time- and resource-hungry training phase, whose requirements dwarf those of the prediction/recommendation phase—has received little to no attention in the literature. This article addresses this gap for a number of representative and highly popular CF models, including algorithms based on matrix factorization, k-nearest neighbors, co-clustering, and slope one schemes. To this end, we first study the computational complexity of the training phase of said CF models and derive time and space complexity equations. Then, using characteristics of the input and the aforementioned equations, we contribute a methodology for predicting the processing time and memory usage of their training phase. Our contributions further include an adaptive sampling strategy, to address the tradeoff between resource usage costs and prediction accuracy, and a framework that quantifies both the efficiency and effectiveness of CF. Finally, a systematic experimental evaluation demonstrates that our method outperforms state-of-the-art regression schemes by a considerable margin, with an overhead that is a small fraction of the overall requirements of CF training.