WeBrowse: Mining HTTP logs online for network-based content recommendation

Content curation refers to the act of assisting users to identify relevant and interesting information in the overwhelming amount of online content available today. Existing curation services rely either on robots, on experts, or on crowdsourcing to discover and promote content. This paper complements these solutions with passive crowdsourced content curation, an approach that leverages the passive observation of user clicks as an indication of users’ interest in a piece of content. Passive crowdsourcing is particularly promising for communities of a place (e.g., campus or enterprises), where users share common interests but fail to actively share content. We design, implement, and evaluate WEBROWSE, a passive crowdsourced system for content curation. WEBROWSE requires no active user engagement to promote content. Instead, it extracts the URLs users visit from traffic traversing a network link to identify popular and interesting content. We prototype WEBROWSE and evaluate it using ...

• Type: Journal
• Year: 2016
• Where: CORR
• Authors: Giuseppe Scavo, Zied Ben-Houidi, Stefano Traverso, Renata Teixeira, Marco Mellia
• Keywords: CORR 2016, Education