Rowan Nairn

Short and tweet: experiments on recommending content from information streams

More and more web users keep up with newest information through information streams such as the popular micro-blogging website Twitter. In this paper we studied content recommendation on Twitter to better direct user attention. In a modular approach, we explored three separate dimensions in designing such a recommender: content sources, topic interest models for users, and social voting. We implemented 12 recommendation engines in the design space we formulated, and deployed them to a recommender service on the web to gather feedback from real Twitter users. The best performing algorithm improved the percentage of interesting content to 72% from a baseline of 33%. We conclude this work by discussing the implications of our recommender design and how our design can generalize to other information streams.

Signpost from the masses: learning effects in an exploratory social tag search browser

Social tagging arose out of the need to organize found content that is worth revisiting. A significant side effect has been the use of social tagging sites as navigational signposts for interesting content. The collective behavior of users who tagged contents seems to offer a good basis for exploratory search interfaces, even for users who are not using social bookmarking sites. In this paper, we present the design of a tag-based exploratory system and detail an experiment in understanding its effectiveness. The tag-based search system allows users to utilize relevance feedback on tags to indicate their interest in various topics, enabling rapid exploration of the topic space. The experiment shows that the system seems to provide a kind of scaffold for users to learn new topics.

Precision-focused Textual Inference

This paper describes our system as used in the RTE3 task. The system maps premise and hypothesis pairs into an abstract knowledge representation (AKR) and then performs entailment and contradiction detection (ECD) on the resulting AKRs. Two versions of ECD were used in RTE3, one with strict ECD and one with looser ECD.

Mail2Tag: Augmenting email for sharing with implicit tag-based categorization

New technology can disrupt existing social processes, especially those formed within the workplace email habitat. Recent abundance of sharing tool choices and disruption of practices makes for a lack of agreement and coherence in the use of information sharing tools. At work, email remains the primary way for sharing information, despite years of knowledge management research. We examine the design of a system for lightweight organizational sharing called Mail2Tag, which augments email by utilizing existing email sharing practices to help gather content, implicitly organize that content, and evolve both the shared content and the groups of people interested in that content. The vision is to get the right information to the right people at the right time, without increasing overall information noise.

Studying the Adoption of Mail2Tag: an Enterprise2.0 Tool for Sharing

The Mail2Tag system leverages existing practices around enterprise email to move relevant information out from individual inboxes. With Mail2Tag users share information by emailing content to a special email address, such as CC to sometag@share.company.com, where ‘sometag’ can be any keyword. The system then adaptively redistributes the information based on profiles inferred from prior user activity in the system. In this way no changes to the email client are required for users to participate in the system and information is routed based on individual need, while the amount of information noise is reduced. We study the Mail2Tag system and its 20-month deployment in an organization as a lens to understand how to measure the adoption for this type of tool for sharing. We assess adoption via quantitative and qualitative measures and identify key factors that facilitate or constrain adoption. Our findings suggest that perceived usefulness is a key facilitator and that people are drawn to different levels of use depending on their social role in the organization. Each level of use is a valuable contribution in itself and should be accounted for when assessing adoption.