www 2013

Greatly organized conference. Attendees especially liked the “Brazilian typical dinner”, pic below ;)

What did I do in Rio? Here we shall focus on the professional bit of my visit ;) On Monday, I gave a keynote at the workshop on  ”Making Sense of Microposts“. I summarized the work I have been doing for the last year or so -  Urban*: Crowdsourcing for the Good of London  (slides). I also briefly mentioned what I then presented on Friday: Psychological Maps 2.0 (slides). The idea behind this work is that planners and social psychologists have suggested that the recognizability of the urban environment is linked to people’s socio-economic well-being. We built a web game that puts the recognizability of London’s streets to the test. It follows as closely as possible one experiment done by Stanley Milgram in 1972. We  found strong correlations suggesting that the more recognizable a neighborhood, the more socio-economic comfortable the neighborhood (less crime, better living environment). This has interesting implications for urban planning,  for location-based services (profiling&personalization of mobile services), and for web engagement studies (stay tuned for our future work!). With Jisun and Jon, I also had a poster on Fragmented Social Media: A Look into Selective Exposure to Political News.

As for other Yahoo!ers , Gianmarco gave a keynote at the Real-Time Analysis and Mining of Social Streams. He introduced a platform for mining big data streams called SAMOA – really high-impact work! Mounia enjoyed an impressive buzz on Twitter with her tutorial on measuring user engagement (the slides are detailed enough to  read beautifully). Bart presented his work with Adam about segmenting space (e.g., USA map) solely based on geo-referenced picture tags. The work featured  an impressive demo, which I really hope will be publicly available soon.

Papers I found interesting include:

Trade Area Analysis using User Generated Mobile Location Data
This is about “identifying the activity center of a mobile user, profiling users based on their location history, and modeling users’ preference probability.” interesting applications of this work include determination of trade Area Boundary using Check-ins; and Location-based User Profiling.

Do Social Explanations Work? Studying and Modeling the Effects of Social Explanations in Recommender Systems
very interesting topic in recsys – explanability! “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.”

Hierarchical Geographical Modeling of User Locations from Social Media Posts
Google folks proposed an integrated generative model of location and message content (tweets). this model can predict location just based on tweets. more specifically, they are able to “obtain accurate estimates of the location of a user

based on his tweets and to obtain a detailed estimate of a geographical language model.”

MSR friends show how user demographic traits such as age and gender, and even political and religious views can be efficiently and accurately inferred based on their search query histories. “This is accomplished in two steps; we first train predictive models based on the publically available myPersonality dataset containing users’ Facebook Likes and their demographic information. We then match Facebook Likes with search queries using Open Directory Project categories. Finally, we apply the model trained on Facebook Likes to large-scale query logs of a commercial search engine while explicitly taking into account the difference between the traits distribution in both datasets. “

Aggregating Crowdsourced Binary Ratings
“In this paper we analyze a crowdsourcing system consisting of a set of users and a set of binary choice questions. Each user has an unknown, fixed, reliability that determines the user’s error rate in answering questions. The problem is to determine the truth values of the questions solely based on the user answers. “

No Country for Old Members: User Lifecycle and Linguistic Change in Online Communities
This won the best paper award. Users of online communities follow a “two-stage lifecycle with respect to their susceptibility to linguistic change: a linguistically innovative learning phase in which users adopt the language of the community followed by a conservative phase in which users stop changing and the evolving community norms pass them by. Building on this observation, we show how this framework can be used to detect, early in a user’s career, how long she will stay active in the community.”

From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise Through Online Reviews
In a vein similar to the previous paper, they ” model how tastes change due to the very act of consuming more products— in other words, as users become more experienced.” it’s a very nice addition to the recsys literature

Timespent Based Models for Predicting User Retention
Another way of predicting a user’s lifetime. The authors “attempt to address the problem of predicting user retention based on the user’s previous sessions. The paper first explores the different user and content features that are helpful in predicting user retention.

WTF: The Who to Follow Service at Twitter
directly from twitter folks. the paper gets interested in section 5 for me. i didn’t know that twitter used salsa.

Organizational Overlap on Social Networks and its Applications
another way of doing link prediction by linkedin. ” computing the probability of connection between two people based on organizational overlap (based on the users belonging to organizations such as companies, schools, and online groups) “

Spatio-Temporal Dynamics of Online Memes: A Study of Geo-Tagged Tweets
James presented this cool paper. very very interesting metrics in there like hashtag’s: focus; entropy; and spread. they found that majority of hashtags have a small spread. they also measured a city’s capability of spreading ideas (=hashtags) globally and found spray & diffuse patterns seen in previous paper (scellato’s paper on youtube videos in WWW’12). these findings might results into interesting applications, e.g., predicting the popularity of videos based on the country; given an idea, predicting the popularity of the idea; learning spatial granularities for spatio-temporal DBs ;) It would be cool to expand the work by looking at different types of boundaries: language boundaries, ideological boundaries (west vs. east coasts), and cultural boundaries.

Diversified Recommendation on Graphs: Pitfalls, Measures, and Algorithms
The diversification problem is usually addressed as a bicriteria objective optimization problem of relevance and diversity…we propose a novel measure called expanded relevance which combines both relevance and diversity into a single function in order to measure the coverage of the relevant part of the graph.

Wisdom in the Social Crowd: an Analysis of Quora
the first analysis of quora i’ve seen. very nice

Voices of Victory: A Computational Focus Group Framework for Tracking Opinion Shift in Real Time
they propose a nice way of real-time tracking opinion shift in social media. “Our approach uses prior user behaviors to detect users’ biases, then groups users with similar biases together. We track the behavior streams from these like-minded sub- groups and present time-dependent collective measures of their opinions. These measures control for the response rate and base attitudes of the users, making shifts in opinion both easier to detect and easier to interpret. “

Gender Swapping and User Behaviors in Online Social Games
If you are into changing sex, virtually i meant, you might be interested in this paper. it studies ““gender swapping” in multiplayer games which refers to players choosing avatars of genders opposite to their natural ones.” unfortunately, i missed the presentation and could not enjoy Juyong in cross-dressing attire.

Predicting Group Stability in Online Social Networks
“We build models to predict if a group is going to remain stable or is likely to shrink over a period of time. We observe that both the level of member diversity and social activities are critical in maintaining the stability of groups. We also find that certain ‘prolific’ members play a more important role in maintaining the group stability. “

cute cross-platform work. “We specifically aim at understanding if the user’s profile information in a social network (for example Facebook) can be leveraged to predict what categories of products the user will buy from (for example eBay Electronics). “

- @danielequercia

Comments are closed.