pytopicgram: A library for data extraction and topic modeling from Telegram channels
SoftwareX
(under review)
(SUBMITTED)
Abstract:
Telegram has emerged as a critical platform for public communication, offering vast amounts of semi-structured data through its public channels. \pytopicgram is a Python library designed to facilitate the extraction, processing, and categorization of Telegram channels’ messages, enabling researchers to analyze content efficiently. The tool supports fast, flexible message retrieval, extended channel data collection, engagement metrics calculation, and advanced topic modeling, offering valuable insights into content dissemination and audience interaction. This paper outlines the architecture, functionalities, and impact of \pytopicgram\,providing practical use examples. The versatility of \pytopicgram makes it a powerful solution for researchers and analysts investigating public discourse on Telegram.
Links:
DOI: PDF: |
Bibtex:
@article{GomezRomero2025, author = {Gómez-Romero, Juan and Cantón-Correa, Javier and Pérez-Mercado, Rubén and Prados-Abad, Francisco and Molina-Solana, Miguel and Fajardo, Waldo}, title = {pytopicgram: A library for data extraction and topic modeling from Telegram channels}, journal = {SoftwareX}, year = {SUBMITTED}, volume = {(under review)}, doi = {}, comment = {}, timestamp = {43} }