Posts Tagged ‘research ’
Back when I was just starting graduate school, I remember already feeling as if I understood the components needed for great scientific research: knowledge of a domain, the ability to implement a system or execute an experiment, and a creative insight about a phenomenon worth studying. While the domain knowledge and ability to execute seemed like pre-requisites for doing science at all, the capacity for creativity seemed to the element that separated a great scientist from the good. Since I felt like I was good at identifying creative research, I hoped that once I immersed myself in academia and started gaining domain knowledge and engineering skill, the creative ideas would come to me. Now, almost a year into my PhD program, I feel like I have learned a great deal, but I am left with the question: Where are all those good ideas?
I’m embedding a presentation I gave at a recent “Data Lunch” about how to analyze responses to Likert items. As I am not a stats expert in any respect, I learned a number of things while putting this together – one of the most important is that Likert isn’t actually pronounced “Like-ert”, it’s pronounced “Lick-ert”, which is still tough for me to remember to say. Anyways, hope you enjoy, I’ll include some summary below as well.
I’ve been interested for a while now in how information and behavior can spread through social networks; an important sub-topic in this field is the spread of health behaviors. This area of study is especially important in understanding the behaviors of adolescents, as there are a number of unhealthy behaviors (ranging from drug use to unhealthy eating to unsafe sex practices) which start in adolescence, persist into adulthood, and contribute to some of the leading causes of death and disability.
As any parent or educator will likely tell you, the behavior of teens closely linked in a social network will often display many similarities: teens who smoke or drink, for instance, are often friends with other teens who smoke or drink. By establishing and tracking the spread of these behaviors scientifically, we can gain a greater understanding of the mechanisms at work and perhaps harness them to help spread healthy behaviors instead of unhealthy ones.
I decided to try a little Mechanical Turk study to see if I could spot some differences between tags generated by experts and those generated by novices. I had each Turker read 1 of 5 web pages (on the topic of “enterprise 2.0 mashups”) and enter 5 tags which they thought would be useful for bookmarking the page (either for themselves or others). I also asked them to rate how familiar they were with the subject matter (“Not at All”, “Slightly Familiar”, “Somewhat Familiar”, and “I am an Expert”)…
Earlier this week, the team at Aardvark unveiled a new paper “The Anatomy of a Large-Scale Social Search Engine” which will be presented in April at WWW 2010. Inspired by and patterned after “The Anatomy of a Large-Scale Hypertextual Web Search Engine”, which describes the PageRank algorithm which drives Google’s search ranking system (which as Aardvark’s blog points out, was also presented at WWW 12 years ago). The paper, by Aardvark’s Damon Horowitz and Stanford’s Sep Kamvar, focuses mostly on the architecture of the Aardvark system, from the external representations with which users interact to the internal ranking algorithms on which the system runs. Below, I present a short summary of what they report, focusing on the elements I found most interesting.
I recently received an email message announcing the creation of a new journal, entitled The Journal of Serendipitous and Unexpected Results (JSUR), which focuses on reporting research efforts that differ from “what is traditionally thought of as a publishable result.” They are looking for papers in both Computer Science and Life Science.
Last month, I read a study by B. J. Fogg and others from the Persuasive Technology Lab at Stanford, entitled “What Makes Web Sites Credible? A Report on a Large Quantitative Study”. The paper described an early effort to systematically determine how different elements of web sites affect people’s perceptions of credibility (defined roughly as the intersection of trustworthiness and expertise). The original study design had 1400 participants completing a survey which presented them with 51 web site elements and asked them to rate how much more or less each element would affect the believability of a web site. The two questions I hope to answer, roughly, are “What has changed in the past 10 years about how people assess web site credibility?” and “Is there a cheaper, yet effective, way to do a study like this?”. The results have implications for website design.
These are some slides from a presentation I gave on some Mechanical Turk data I collected about how people are using Activity Streams. Specifically, I was interested in what tools people were using, what they were using them for, how these tools might be improved, and how people had been using these tools to collaborate/coordinate. Here’s what I found…
