Dan Cosley

Bin Xu, Liang Gou, Anbang Xu et al.

Users' persistent social media contents like posts on Facebook Timeline are presented as an "exhibition" about the person to others, and managing these exhibitional contents for impression management needs intentional and manual efforts. To raise awareness of and facilitate impression management around past contents, we developed a prototype called PersonalityInsight. The system employs computational psycho-linguistic analysis to help users visualize the way their past text posts might convey impressions of their personality and allowed users to modify their posts based on these visualizations. We conducted a user study to evaluate the design; users overall found that such a tool raised awareness of the fact and the ways personality might be conveyed through their past content as one aspect of impression management, but that it needs design improvement to offer action-able suggestions for content modification, as well as careful thinking about impression management as one of many values people have about their digital past.

Amit Sharma, Dan Cosley

Many online social networks thrive on automatic sharing of friends' activities to a user through activity feeds, which may influence the user's next actions. However, identifying such social influence is tricky because these activities are simultaneously impacted by influence and homophily. We propose a statistical procedure that uses commonly available network and observational data about people's actions to estimate the extent of copy-influence---mimicking others' actions that appear in a feed. We assume that non-friends don't influence users; thus, comparing how a user's activity correlates with friends versus non-friends who have similar preferences can help tease out the effect of copy-influence. Experiments on datasets from multiple social networks show that estimates that don't account for homophily overestimate copy-influence by varying, often large amounts. Further, copy-influence estimates fall below 1% of total actions in all networks: most people, and almost all actions, are not affected by the feed. Our results question common perceptions around the extent of copy-influence in online social networks and suggest improvements to diffusion and recommendation models.

Amit Sharma, Dan Cosley

People regularly share items using online social media. However, people's decisions around sharing---who shares what to whom and why---are not well understood. We present a user study involving 87 pairs of Facebook users to understand how people make their sharing decisions. We find that even when sharing to a specific individual, people's own preference for an item (individuation) dominates over the recipient's preferences (altruism). People's open-ended responses about how they share, however, indicate that they do try to personalize shares based on the recipient. To explain these contrasting results, we propose a novel process model of sharing that takes into account people's preferences and the salience of an item. We also present encouraging results for a sharing prediction model that incorporates both the senders' and the recipients' preferences. These results suggest improvements to both algorithms that support sharing in social media and to information diffusion models.

Amit Sharma, Dan Cosley

Recommender systems associated with social networks often use social explanations (e.g. "X, Y and 2 friends like this") to support the recommendations. We present a study of the effects of these social explanations in a music recommendation context. We start with an experiment with 237 users, in which we show explanations with varying levels of social information and analyze their effect on users' decisions. We distinguish between two key decisions: the likelihood of checking out the recommended artist, and the actual rating of the artist based on listening to several songs. We find that while the explanations do have some influence on the likelihood, there is little correlation between the likelihood and actual (listening) rating for the same artist. Based on these insights, we present a generative probabilistic model that explains the interplay between explanations and background information on music preferences, and how that leads to a final likelihood rating for an artist. Acknowledging the impact of explanations, we discuss a general recommendation framework that models external informational elements in the recommendation interface, in addition to inherent preferences of users.

Shyong, K. Lam, David M Pennock et al.

We exploit the redundancy and volume of information on the web to build a computerized player for the ABC TV game show 'Who Wants To Be A Millionaire?' The player consists of a question-answering module and a decision-making module. The question-answering module utilizes question transformation techniques, natural language parsing, multiple information retrieval algorithms, and multiple search engines; results are combined in the spirit of ensemble learning using an adaptive weighting scheme. Empirically, the system correctly answers about 75% of questions from the Millionaire CD-ROM, 3rd edition - general-interest trivia questions often about popular culture and common knowledge. The decision-making module chooses from allowable actions in the game in order to maximize expected risk-adjusted winnings, where the estimated probability of answering correctly is a function of past performance and confidence in in correctly answering the current question. When given a six question head start (i.e., when starting from the $2,000 level), we find that the system performs about as well on average as humans starting at the beginning. Our system demonstrates the potential of simple but well-chosen techniques for mining answers from unstructured information such as the web.