Recommendation approaches generally fail to recommend newly-published papers as relevant, owing to the lack of prior information about the said papers and, more particularly, problems associated with cold starts. It would appear, to all intents and purposes, that researchers currently interact more on social networks than they normally would in academic circles, and relationships of a purely academic nature have witnessed a paradigm shift, in keeping with this new trend. In existing paper recommendation methods, the social interaction factor has yet to play a pivotal role. The authors propose a social network-based research paper recommendation method, that alleviates cold start problems by incorporating users' social interaction, as well as topical relevancy, among assorted papers in the Mendeley academic social network using a novel approach, random walk Ergodic Markov Chain. The system yields improved results after cold start alleviation, compared with the existing system.

Geographical knowledge resources or gazetteers that are enriched with local information have the potential to add geographic precision to information retrieval. We have identified sources of novel local gazetteer entries in crowd-sourced OpenStreetMap and Wikimapia geotags that include geo-coordinates. We created a fuzzy match algorithm using machine learning (SVM) that checks both for approximate spelling and approximate geocoding in order to find duplicates between the crowd-sourced tags and the gazetteer in effort to absorb those tags that are novel. For each crowd-sourced tag, our algorithm generates candidate matches from the gazetteer and then ranks those candidates based on word form or geographical relations between each tag and gazetteer candidate. We compared a baseline of edit distance for candidate ranking to an SVM-trained candidate ranking model on a city level location tag match task. Experiment results show that the SVM greatly outperforms the baseline.

No abstract

No abstract