🔍 Analyze PDF files effectively with this Python tool, testing compatibility across libraries to guide optimal PDF processing solutions.

An R-tool for comprehensive science mapping analysis. A package for quantitative research in scientometrics and bibliometrics.

Inference of microbial interaction networks from large-scale heterogeneous abundance data

Code and data for extracting co-occurrence networks from Shakespeare's plays

The Document Statistics Analyzer is a Python tool that analyzes text documents (PDF, DOCX, TXT), providing word, sentence, paragraph, and document-level insights. It generates reports in Markdown, HTML, or PDF with visualizations like word clouds and sentiment heatmaps, packaged in a ZIP archive, using NLTK, spaCy, and Gradio.

This repository contains the data used for and generated during our research for the article "Neo-Assyrian Imperial Religion Counts: A Quantitative Approach to the Affiliations of Kings and Queens with Their Gods and Goddesses." The creation of this data has been funded by the Academy of Finland (decision numbers 298647, 312051, and 330727).

Scripts to convert correlation and p-value matrices to edge list and network

It is important for a granting agency to know how the distribution of the applications qua disciplines is. ˆ How many applications belong to Exact Science disciplines, how many fall within one discipline? ˆ How many applications with disciplines outside exact sciences domain have been submitted?

Compared the agenda setting strategies on the "Ractopamine Pork" Vote, one of the four questions in the 2021 Taiwanese Referendum, between pan-blue and pan-green media by using text mining approaches such as bag-of-words, w2v, topic model. Raw data were collected from four Taiwanese media (Chinatimes/TVBS/LTN/FTV) with Python Package BeautifulSoup.

NLP Project 2 - Using ount Vector, TF-IDF Vector, Co-occurrence Matrix for Frequency based embeddings and made Word2Vec model using Continuous Bag of Words (CBOW) and Skip-Gram (SG) for Prediction based Embeddings

R package for analyzing microbial co-occurences

Text Processing Using Hadoop

Calculates the probability of co-occurrence from gray-scale images.

Texture Segmentation using: Gray-Level Co-occurence Matrix, Leung-Malik (LM) Filter Bank and Schmid (S) Filter Bank and Local Binary Pattern.

Co-occurrence Based Texture Synthesis

Work in Fintech-Text-Mining-and-Machine-Learning class

A fast implementation of GloVe, with optional retrofitting

Data aggregation | Big Data Analysis | Visualization