Can I get details about the algorithms used for classifying questions in stackoverflow ("Questions that may already have your answer"). Most of the suggestions I get are nowhere related to the question I have intended to ask.
I do not believe that StackExchange has published precisely what algorithm(s) they use for that, so we can't tell for sure.
However, in this meta.stackexchange question, you can follow some of the efforts that were undertaken in collecting training data for training such a classifier. The post also links to the "CQADupStack: Gold or Silver?" paper which describes the analysis of such a dataset that comes directly from StackOverflow. You might be able to find interesting literature by browsing google scholars for papers that cite this paper.
There is also another meta.stackoverflow discussion on this topic, where answers link to various community-developed projects / bots for this purpose. Again, not necessarily what is actually used by the StackExchange sites, but likely similar.
Finally, there is definitely a lot of research on performing such classifications (one example found by a quick google search is "Duplicate Question Detection in Stack Overflow: A Reproducibility Study", where many other relevant publications can be found in the list of References). This again does not necessarily lead to be precisely the algorithm that StackExchange happens to use, but many relevant ones, one or more of which they might be using.