About: Author Name Disambiguation using Random Forest and Gradient Boosted Tree Classifier

Author: The scripts have been written by Mr. Kaushal Jhawar. Reference paper: Kaushal Jhawar, Debarshi Kumar Sanyal, Samiran Chattopadhyay, Plaban Kumar Bhowmick, and Partha Pratim Das. (2020, August). Author name disambiguation in PubMed using ensemble-based classification algorithms. In Proceedings of the ACM/IEEE Joint Conference on Digital Libraries (JCDL), Xi’an, Shaanxi, P. R. China, 1-4 August, 2020. (Please cite the above paper if you use our program in your research/applications. We would also love your hear your feedback.)

Programming Language: Python 3.7.0

Operating System: 64 bit - Windows 10, x64 based processor. Ubuntu 18.04.1 LTS

External Dependencies: Biobert_v1.1_pubmed: https://github.com/naver/biobert-pretrained. Version: BioBERT-Base v1.1 (+ PubMed 1M) - based on BERT-base-Cased (same vocabulary)

Python Libraries Required: pyjarowinkler, xlsxwriter, xlrd, collections, bs4, nltk, openpyxl, numpy, flair (for embeddings and data), gensim (for Word2Vec), pandas, sklearn, matplotlib, json

Instruction to Run the Code: Follow the “Step_to_run_code.txt”

Input to the model: Dataset in the current working directory. There is no command line input, already coded in the script.

Output by the model: Printed during the execution of the python program.