pubmlp

Multimodal publication classifier with LLM and deep learning. Fuses transformer embeddings from Hugging Face with tabular features through a multilayer perceptron (MLP) on PyTorch for human-in-the-loop screening. Screen by matched rules, by semantic similarity through sentence-transformers, by the classifier with active learning, or by a language model as a second rater. Read exports in every format bibliometrix accepts, extract page-anchored evidence with pdfplumber, and report stopping criteria and automation use for PRISMA.

Installation

pip install pubmlp

With optional dependencies:

pip install "pubmlp[screening]"  # regex and semantic screening, stratified sampling
pip install "pubmlp[fulltext]"   # PDF reading with page-anchored evidence
pip install "pubmlp[benchmark]"  # SYNERGY benchmark datasets

From GitHub:

pip install git+https://github.com/mshin77/pubmlp.git

Getting Started

See Quick Start and Screening Workflow for tutorials.

Citation

Shin, M. (2026). pubmlp: Multimodal publication classifier with LLM and deep learning (Python package version 0.6.1) [Computer software]. https://github.com/mshin77/pubmlp

Reference

Shin, M., & McKenna, J. (2026). Exploring the research landscape on single-case design methodology using technology through text mining and large language models. Journal of Behavioral Education. https://doi.org/10.1007/s10864-026-09630-1

Metadata

Release files for pubmlp 0.6.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for pubmlp 0.6.1
File	Size	Uploaded
pubmlp-0.6.1.tar.gz	60.7 kB	Sep 13, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for pubmlp 0.6.1
File	Interpreter	ABI	Platform	Reset
pubmlp-0.6.1-py3-none-any.whl 67.4 kB Sep 13, 2026	Python 3	none	any	Details

Total release size: 128.1 kB

Release files / pubmlp-0.6.1.tar.gz

Download URL	pubmlp-0.6.1.tar.gz
Size	60.7 kB
Tags	Source
SHA-256 checksum How to use checksums	`50340b472f33cf70d55db0658151839d2a6b8785b4799f12a1ad07d019b66469`
BLAKE2b-256 checksum How to use checksums	`53c402d49e754019bd9be0e9e5a13eb4efd9d9a0a12e0d3c83d4fd4df7d100b1`
Upload date	Sep 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.9`

Release files / pubmlp-0.6.1-py3-none-any.whl

Download URL	pubmlp-0.6.1-py3-none-any.whl
Size	67.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`57e267315a965e5268a25d812df396e27c62fbb2c5f75eac02ec2bc03745128a`
BLAKE2b-256 checksum How to use checksums	`d07b1359112cd17cac0ade3879d11ae1374586d3809052e2513a9b0b89aba058`
Upload date	Sep 13, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.13.9`