A new paper on the search innovation was published by Ronak Pradeep, a聽computer science PhD student, co-authored with his supervisor Jimmy Lin, postdoctoral fellow聽Rodrigo Nogueira and graduate student聽Xueguang Ma.
The paper highlights significant results including an聽80 per cent improvement in searches, compared to baseline, to help people make better decisions about topics like COVID.
Search engines are the most common tools the public uses to look for facts about COVID-19 and its effect on their health. A proliferation of misinformation can have real consequences in terms of not only public health聽but also聽general social cohesiveness and confidence in institutions.聽
鈥淲ith so much new information coming out all the time, it can be challenging for people to know what鈥檚 true and what isn鈥檛,鈥 said Pradeep. 鈥淏ut the consequences of misinformation can be pretty bad, like people going out and buying medicines or using home remedies that can hurt them.鈥
Even the big search engines that host billions of searches every day can鈥檛 keep up, he said, since there has been so much scientific data and research on COVID-19 in such a short time.
鈥淢ost of the systems are trained on well-curated data, so they don鈥檛 always know how to differentiate between an article promoting drinking bleach to prevent COVID-19 as opposed to real health information,鈥 Pradeep said.
鈥淥ur goal is to help people see the right articles and get the right information so they can make better decisions in general with things like COVID.鈥
Pradeep said the project aims to refine search programs to promote the best health information for users. He and his research team have leveraged their two-stage neural reranking architecture called mono-duo-T5 for search which they augmented with Vera, a label prediction system trained to discern correct from dubious and incorrect information.
The system links with a search protocol that relies on data from the World Health Organization and verified information as the basis for ranking, promoting and sometimes even excluding online articles.
A recent paper with results from preliminary testing of the system, 鈥,鈥 with co-authors Pradeep, Ma, Nogueira and聽Lin, was recently published in聽SIGIR 鈥21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.