Search Engine for Computer Science Research Papers.

Dataset used - Aminer Dataset contains citation data is extracted from DBLP, ACM, MAG (Microsoft Academic Graph), and other sources. The first version contains 629,814 papers and 632,752 citations.
Search Engine - Elastic Search API
Models implemented - Word2vec, Doc2vec, PageRank.
Also performed classification and clustering of research papers based on feature selection methods like chi-squared and mutual information

Name		Name	Last commit message	Last commit date
Latest commit History 12 Commits
.ipynb_checkpoints		.ipynb_checkpoints
0295aaa9a4d4acab4a0d-b7df7b6db52b7543336cced67fc4b6e781f5f0b1		0295aaa9a4d4acab4a0d-b7df7b6db52b7543336cced67fc4b6e781f5f0b1
Doc2vec,NB,Naive Bayes,SVM,Logistic regression-Copy1.ipynb		Doc2vec,NB,Naive Bayes,SVM,Logistic regression-Copy1.ipynb
Information_Retrieval_Report.pdf		Information_Retrieval_Report.pdf
NB,SVM,Logistic regression,PCA and K-means on TFIDF .ipynb		NB,SVM,Logistic regression,PCA and K-means on TFIDF .ipynb
README.md		README.md
Untitled.ipynb		Untitled.ipynb
clean_id_title.txt		clean_id_title.txt
icse_id.txt		icse_id.txt
sigmod_id.txt		sigmod_id.txt
vldb_id.txt		vldb_id.txt

Provide feedback