Microsoft on Monday said that it is currently working with professors from the Indian Institute of Technology (IIT) Kharagpur in order to build a system that can form the basis for a deeper and more meaningful search engine.
In a bid to take on arch rivals Google, American multinational technology conglomerate Microsoft on Monday said that it is currently working with professors from the Indian Institute of Technology (IIT) Kharagpur in order to build a system that can form the basis for a deeper and more meaningful search engine. “The new search engine could assist users looking for subjective information and trusted opinions,” the company said in a statement. The name of the web search engine is Bing which is owned and operated by Microsoft.
While current search engine algorithms are great at working with fact-based queries and providing structured answers, they are surprisingly ineffective at answering subjective and personal questions. According to a report by IANS, Microsoft’s Senior Applied Researcher Manish Gupta partnered with professors from IIT Kharagpur in order to conduct a study on extracting meaningful information from social conversations to help search engines answer social list queries better by deploying artificial intelligence and machine learning.
Such queries based on human experiences and personal opinions are not easy for a standard search engine to comprehend and hence at several instances they fail to answer questions such as – ‘How to make small talk with new friends’, ‘People’s favourite memories from school’, ‘How does it feel to immigrate to a new country and many more’.
In order to come up with a solution for the same, the team used multi-word hashtags, basically idioms, from Twitter to conduct a detailed study so that the search engine could give more accurately.
“While traditional search engines may struggle with such deeply human queries there are online platforms specifically tailored for personal opinions and conversations — social media. Twitter, specifically, has become a forum for people to create sustained online conversations held together by a common hashtag,” Gupta told IANS.
According to the report, the researchers collected around four million hashtags that were trending between January 2015 and June 2015, and used a SVM (Support Vector Machine) classifier to conduct this research. Some of these hashtags were #foreveralone, #awkwardcompanynames, #childhoodfeels, and #africanproblems.
“The algorithm used to conduct this study forms the basis for a better search engine for social platforms which can assist users looking for subjective information and trusted opinions,” the company statement said.