markostam / academic-citation-prediction

Predicting the impact of academic papers using computer vision and text features.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Machine Analysis of High Impact Research to through Text and Image Analysis

System to automatically classify an academic paper with respect to the number of citations it will receive based on a combination of visual and text features. A scraper was written to automatically collect academic PDF's and their corresponding number of citations. Visual and text classifiers were then built and tied together with a metaclassifier. Tool used include python, scrapy, opencv and sklearn.

About

Predicting the impact of academic papers using computer vision and text features.


Languages

Language:Python 97.2%Language:Shell 2.8%