Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{151918,
        author = {Vishwajeet Rapte and Amit Khebade and Sawani Sapkal and Shaheen Yasmin and Amol Lachake},
        title = {System to Rank Results in CQA Sites},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {8},
        number = {1},
        pages = {1245-1249},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=151918},
        abstract = {Question Answering (CQA) is a specially designed and an appropriate form to retrieve information. An available set of credentials, a Question Answering system bids to fetch the correct answers to questions which are posed. For the purpose to discover a similar question from available data means historical data records has been put to question answering, with great hypothetical and sensible achievement and hence users have to allusion with credentials or even identical passage as the majority of the data recovery systems before finding the correct one answer. To deal with such issues, there is a need of a system that permits users to ask a question in daily language as well as get an answer quickly and concisely, with enough contexts to constitute the answer. Since users move violently to find the way the prosperity of online data currently obtainable, the required for automatic question answer system becomes most vital. A proposed system defines a new system to grade answer candidates via pair wise comparison. In proposed system, it includes two type of elements, Offline Learning as well as Online Search. The systemspecies out the answer candidates through influencing the offline trained form to examine the priority orders. The data-driven drawcan produce higher level presentation and complement conventional question answering methods which are motivated through data withdrawal.},
        keywords = {Community question answering, Rake_nltk, K-nearest neighbor, Word embeddings},
        month = {},
        }