OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Data & Analytics

Tweet Stance Prediction

Tweet Stance Prediction is an open-source research repository of Jupyter notebooks that demonstrate transfer-learning approaches for classifying tweets about a topic as Favor, Against or None. It includes ULMFiT and transformer workflows and a Perl script for SemEval-style F1 evaluation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Tweet Stance Prediction — OpenViST project profile in AI Data & Analytics.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it as a notebook-based research reference when exploring topic-specific tweet stance classification or evaluating predictions in the documented SemEval-compatible format.

Who it is for

  • Researchers and students exploring NLP transfer learning for tweet stance classification.
  • Python practitioners seeking notebook examples and an evaluation script for topic-focused stance labels.

Documented uses

  • Classify tweets about a selected topic into Favor, Against or None using the demonstrated notebook workflows.
  • Compare ULMFiT and transformer approaches to stance classification.
  • Evaluate stance predictions with the included SemEval-oriented F1 scoring script.
Before you choose

Requirements & limits

The repository is public and identifies its license as MIT.

  • The repository provides notebooks and a scoring script rather than a documented hosted classification interface.
  • The ULMFiT workflow uses fastai v1 and requires spaCy’s English model; the README specifies Python 3.6+ and PyTorch 1.0+.
  • The evaluation script expects tab-separated files containing ID, target, tweet and stance fields.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the ULMFiT notebook environment

Prepare the documented Python environment and dependencies for the ULMFiT workflow.

Before you start

  • Python 3.6 or later
  • The project repository and its requirements files
  • PyTorch 1.0 or later
  • fastai v1 and spaCy’s English language model for the ULMFiT notebook

Steps

  1. Create and activate a Python virtual environment, then install the repository requirements with the commands in the README.

  2. Install the PyTorch requirements using the provided requirements file.

  3. Install fastai and download spaCy’s English model using the README commands.

  4. Open the included ulmfit.ipynb notebook in a Jupyter environment.

Expected outcome

A locally prepared environment for inspecting and working through the ULMFiT stance-classification notebook.

Guide limitations

  • The README describes the setup but does not establish compatibility with current dependency versions or guarantee successful notebook execution.
  • The guide covers environment preparation and notebook access, not a completed prediction run.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
prrao87/tweet-stance-prediction · Official homepage title · retained in its source language
How we review sourcesSuggest a correction