Computer Science Professor Emeritus David Brown and Computer Science Professor Mark Claypool have continued to be surprised and pleased as a conference paper they co-authored in 2001 still gets cited.
The paper, “Implicit Interest Indicators,” about different ways of gathering data on web users’ preferences, won the best paper prize at the 2001 6th International Conference on Intelligent User Interfaces, or IUI.
It also received a lifetime achievement award of sorts in the spring this year, when it was selected for the 2024 IUI Impact Award, given to papers previously published at the conference that have significantly influenced research or industry practices.
Brown’s and Claypool’s research suggested that web browsers might deduce what users find most interesting based on their interactions and then influence what material is recommended to the user. Such recommender systems require a user interface that can “intelligently'' determine the interests of a user and use this information to make suggestions about appropriate new content to share.
The common solution, explicit ratings, where users tell the system what they think about a piece of information, is well understood and fairly precise. However, having to stop to enter explicit ratings about web pages can disrupt normal patterns of browsing and reading.
A more “intelligent” method is to use implicit ratings, where a rating is obtained by a method other than obtaining it directly from the user. These implicit interest indicators have obvious advantages, including removing the cost of the explicit user rating, and that every user interaction with the system (such as scrolling) might contribute to an implicit rating.
The team built a web browser called “Curious Browser,” installed it on around 40 computers in a WPI lab (on Windows ’98) and logged how users interacted with it. The team reached several conclusions, including that time on page is a good implicit indicator of interest, but that mouse movement and mouse clicks by themselves are not. However, the paper also concluded that mouse clicks combined with keyboard actions–to infer the level of scrolling–were effective indicators of interest.
Then-seniors Phong Le and Makoto Waseda, who did research for the paper as part of their Major Qualifying Project, worked alongside Brown and Claypool.
Brown said he remembers being in the audience at the 2001 conference as the prizes were being given out. He said he heard the “Curious Browser” paper get announced, but it didn’t register right away.
“I sat there and thought, wait a minute, that’s me,” Brown said. He said that 23 years later, it was just as exciting to hear of the impact award.
“[The award] was obviously out of the blue, but when you get more than 1,000 citations, it’s not totally surprising,” Brown said. “To have it recognized by some serious peers is really nice.”
Claypool traveled to the 2024 IUI conference awards ceremony, presenting the paper again with the original slides from 2001.
He said accepting the award at this year’s IUI conference was a rare honor, and a professional first. Even more special, he said, was the chance to reconnect with Le, who joined him on a panel to talk about the paper. Claypool said he was happy to catch up with Le, who went on from WPI to enjoy a successful career in computer security.