PaperPilot

This image displays both the landing page and authentication page.
This image showcases the carousel of interest selection buttons and the thank you page.
API documentation
This image showcases a mail sent by PaperPilot after choosing your interests.

Inspiration

The inspiration behind PaperPilot was to create a platform that simplifies the process of discovering relevant research papers for scholars and researchers. With the abundance of academic papers available online, it can be overwhelming for individuals to find papers that match their research interests. Therefore, we aimed to leverage artificial intelligence to provide personalized recommendations that cater to each user's specific needs.

What it does

PaperPilot is an AI-based research paper recommendation system that provides personalized recommendations to scholars and researchers. The platform employs advanced recommendation algorithms to cluster research papers based on their content and similarity, ensuring accurate and tailored recommendations. The dataset is meticulously curated by scraping research papers from the IEEE website, guaranteeing a vast collection of high-quality academic papers across various domains. The front end of PaperPilot is built using React, providing a seamless and intuitive user experience, and the platform integrates Google Authentication for secure access. Additionally, PaperPilot leverages AWS email services to deliver periodic research paper recommendations directly to users' email inboxes.

How we built it

PaperPilot was built using a combination of technologies. The front end was developed using React, while the back end was powered by Express.js and Flask. We utilized advanced recommendation algorithms like TF-IDF and KNN-like algorithms to cluster research papers based on their content and similarity. The dataset was curated by scraping research papers from the IEEE website, and AWS email services were integrated to deliver periodic research paper recommendations directly to users' email inboxes.

Challenges we ran into

One of the biggest challenges we faced was scraping the research papers from the IEEE website. We had to ensure that the dataset was extensive and high-quality, which required significant effort and time. Additionally, integrating AWS email services and ensuring that the recommendations were delivered accurately and timely was another challenge we faced.

Accomplishments that we're proud of

We are proud of creating a platform that simplifies the process of discovering relevant research papers for scholars and researchers. We are also proud of the advanced recommendation algorithms we developed, which ensure accurate and tailored recommendations based on users' interests.

What we learned

Through developing PaperPilot, we gained valuable experience in utilizing advanced recommendation algorithms like TF-IDF and KNN-like algorithms. We also improved our skills in web development using React, Express.js, and Flask. Additionally, we learned how to integrate AWS email services into a web application.

What's next for PaperPilot

In the future, PaperPilot plans to expand the dataset by including research papers from other academic websites. The platform also aims to incorporate natural language processing (NLP) algorithms to provide more accurate recommendations. Additionally, a feature will be added that allows users to rate and provide feedback on the recommended papers, which will further improve the recommendation algorithms. Other advanced recommendation techniques like collaborative filtering, matrix factorization, and deep learning-based models will be explored to further improve the accuracy and relevance of the recommendations provided by PaperPilot.

To enhance user experience, PaperPilot plans to add more customization options, such as the ability to filter recommendations by publication date, author, or keyword. Additionally, functionalities like saving favorite papers, creating reading lists, and sharing recommendations with colleagues and peers will be added to the platform.

Improving the email recommendation service is also a priority for PaperPilot. The platform wants to provide users with more control over the frequency and content of the emails they receive. Personalization of the email content will also be implemented, highlighting the most relevant papers based on the user's previous interactions with the platform.

Privacy and data security are crucial to PaperPilot. The platform will implement measures to ensure that user data is protected and used only for providing personalized recommendations. Compliance with relevant data protection regulations like GDPR and CCPA is also planned.

Overall, PaperPilot aims to revolutionize the way researchers access and consume academic literature. By leveraging advanced recommendation algorithms, incorporating user feedback, and prioritizing user privacy, PaperPilot seeks to be the go-to platform for researchers and scholars to discover relevant research papers quickly and easily.