Public Behavioral Logs

Large-scale behavioral log analysis allows us to do many things, including build better search engines, predict health epidemics, and support communities through crises. But they can also be hard to come by. This post covers some of the different types of publicly available behavioral logs available for study.

Laser Cutting and Wire Splicing

The transition back to work after the holidays can be hard, with rigorous pseudoscience declaring the first Monday back the most depressing day of the year. Lucky for me, I got to spend Blue Monday (and the rest of the week) having fun laser cutters and LED pixels with Chris, Shelly, Ivan, and Melissa.

How to Ask Effective Questions

We all ask questions of our social networks. For example, the other day I posted a question to Twitter looking for a hotel recommendation in Dublin for SIGIR 2013. When we ask questions, sometimes we get good answers, and sometimes we get bad answers. But the quality of the answers we get isn't completely random – it is something we, as question askers, can control. This post describes some of the tricks we have learned about how to ask effective questions online from our research.

#TwitterSearch

Social networking sites are not just places to maintain relationships. They are also valuable information sources. Previous posts (Online QuestionAsking, Asking v. Searching) have discussed how people find information using social networks by asking questions. This post explores the other way people find information using social media: by searching preexisting social media content.  For example, if someone wanted to read a lot of snarky comments about the use of CamelCase in hashtags, they might go to Twitter and search for "#nowthatchersdead."

Asking v. Searching

Most of the time when we want to know something, we don't turn to a search engine – we ask somebody a question. While we used to have to know the right person to ask, we can now use Facebook or Twitter to broadcast our questions to our entire social network. The kinds of questions that we ask our social networks are very similar to what we search for using search engines, except that we tend to keep our questions "cocktail party-appropriate." Not surprisingly, we are more likely to search about health, religion, sex, and politics than to ask questions on those topics. For example, although adult queries make up a sizable portion of search engine queries, my colleagues and I have yet to see a single question asking about porn in the course of our research.

Online Question Asking

 I do information retrieval research, which means that I try to figure out how people use search engines, and use what I learn from that to build better search algorithms. My goal is to take the short, one or two word query that you enter into a search box and use it to identify a few relevant results from among the billions of documents that make up the web. Something happened a few years ago, however, to change the way that I think about search.