An Efficient Algorithm to Recommend Covid-19 Related Solutions Nirav Das School of Computer Science and Engineering Vellore Institute of Technology, Chennai, 600127, India, nirdas6268@gmail.com Abdul Quadir Md School of Computer Science and Engineering, Vellore Institute of Technology Chennai, 600127, India, abdulquadir.md@vit.ac.in Sreejan Chattopadhyay School of Computer Science and Engineering Vellore Institute of Technology Chennai, 600127, India, chattopadhyaysreejan100@gmail.com Vigneswaran T School of Electronics Engineering Vellore Institute of Technology Chennai, 600127, India, vigneswaran.t@vit.ac.in Karan E Macaden School of Computer Science and Engineering Vellore Institute of Technology, Chennai, 600127, India karanmac21@gmail.com Punitha K School of Computer Science and Engineering Vellore Institute of Technology, Chennai, 600127, India, punitha.k@vit.ac.in Abstract—With the rise of Covid-19, the open-source community has devoted a huge amount of time into developing technical solutions to stop the spread of the virus. Useful solutions like symptom trackers and extensive analysis on existing datasets are a small drop in the massive number of solutions developed by people. But with the massive number of projects or solutions, it is time consuming for a motivated person to find an appropriate solution to put his time into. Therefore, seeing the inspiring amount of work done by the open source community, we are suggesting an efficient algorithm to recommend projects that are Coronavirus related to which the user can get recommendations for projects according to their preference such as language. Keywords— Covid-19, open-source, recommendation system, collaborative filtering, cosine similarity, TF-IDF, bag of words I. INTRODUCTION Covid-19 pandemic has had a profound amount of change in people's lives. The amount of the virus and the fast pace that it spreads has affected the day-to-day life of every person, and has also affected the global economy by slowing it down considerably. Aspects that were almost immediately noticed that were affected by the pandemic are: A. Drastically Reduced Travel With lockdowns in every country, the traveling industry has been massively affected by the pandemic. At the pandemic's peak, it was calculated that the variety of automobiles on the street fell more than 70%. Air travel has plummeted around eighty percent globally with Europe being affected the most. Many airline companies are facing potential closure without help from government bailouts. B. Healthcare Sector One of the most affected areas has been the healthcare sector. The problems caused in this sector range from challenges in diagnosing, isolating, and treating suspected or confirmed cases to disruption of the medical supply chain.Some of the many other challenges that are being faced are the high burden of operating the existing health system. People who are affected by other diseases and health problems are getting ignored. There is a heavy burden on doctors and other healthcare professionals. Another problem is the overburden on medical shops. The pandemic also exposed the lack of technical advancement in medical software systems like app tracking symptoms. There has been a lot of work done by developers, data scientists, and other technical communities on making open- source projects on GitHub on fighting this global pandemic. The projects range from apps tracking symptoms to various analysis being done on the existing data sets. Given the sheer volume, it can be difficult to find a project to contribute and some of the important projects are hard to find due to the way users self-identify their work. There are a wide range of projects covering a variety of languages and topics. Therefore, to contribute to the concerted effort of these open- source projects, one must find the right project according to the skills set by filtering projects. To make this easier, we have built a recommendation system. that can help one find their required project to contribute according to their given set of languages and keywords. II. LITERATURE REVIEW Xia et al produced design of repositories of GitHub recommendation system based on Ternary Closure and HITS Algorithm [1]. In their system they have used the ternary closure theory and the HITS Algorithm. In HITS algorithm, they have calculated the authoritative value of the repository and the user’s hub value. In accordance to the ternary closure theory, the repository information that the user has browsed, the repository the user may be interested in is the upstream repository of the repository he browsed. The results obtained by them are good and the time complexity of the algorithm is also reduced. Zhang et al have detected similar repositories in GitHub [2]. They have mentioned three heuristics in their work. The first heuristic mentions repositories whose readme files which contain similar content are considered to be more similar to one another. The second heuristic mentions that repositories that are starred by users of similar interests are considered to be similar. The third heuristic mentions that repositories which are starred together within a short period of time by the same user are likely to be similar. They have 2022 Third International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT) © IEEE 2022. This article is free to access and download, along with rights for full text and data mining, re-use and analysis. 1635 2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT) | 978-1-6654-1005-2/22/$31.00 ©2022 IEEE | DOI: 10.1109/ICICICT54557.2022.9917800