# Opinions are Made to be Changed: Temporally Adaptive Stance Classification

arXiv: https://arxiv.org/abs/2108.12476 · HTML: https://mlsanity.com/paper/2108.12476/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 27 Aug 2021.

## Builds on (most cited first, 11 of 11)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Statistically Significant Detection of Linguistic Change](https://mlsanity.com/paper/1411.3315/) (2014)
- [Stance and Sentiment in Tweets](https://mlsanity.com/paper/1605.01655/) (2016)
- [Temporal Analysis of Language through Neural Language Models](https://mlsanity.com/paper/1405.3515/) (2014)
- [Cross-Target Stance Classification with Self-Attention Networks](https://mlsanity.com/paper/1805.06593/) (2018)
- [Training Temporal Word Embeddings with a Compass](https://mlsanity.com/paper/1906.02376/) (2019)
- [Discourse-Aware Rumour Stance Classification in Social Media Using Sequential Classifiers](https://mlsanity.com/paper/1712.02223/) (2017)
- [A Tweet Dataset Annotated for Named Entity Recognition and Stance Detection](https://mlsanity.com/paper/1901.04787/) (2019)
- [Every Colour You Are: Stance Prediction and Turnaround in Controversial Issues](https://mlsanity.com/paper/2005.10019/) (2020)
- [QMUL-SDS @ SardiStance: Leveraging Network Interactions to Boost Performance on Stance Detection using Knowledge Graphs](https://mlsanity.com/paper/2011.01181/) (2020)

## Built on by (most cited first, 8 of 8)

- [Large Language Models as Financial Data Annotators: A Study on Effectiveness and Efficiency](https://mlsanity.com/paper/2403.18152/) (2024)
- [Building for Tomorrow: Assessing the Temporal Persistence of Text Classifiers](https://mlsanity.com/paper/2205.05435/) (2022)
- [Evolving Domain Adaptation of Pretrained Language Models for Text Classification](https://mlsanity.com/paper/2311.09661/) (2023)
- [Capturing Stance Dynamics in Social Media: Open Challenges and Research Directions](https://mlsanity.com/paper/2109.00475/) (2021)
- [Examining Temporalities on Stance Detection towards COVID-19 Vaccination](https://mlsanity.com/paper/2304.04806/) (2023)
- [The emojification of sentiment on social media: Collection and analysis of a longitudinal Twitter sentiment dataset](https://mlsanity.com/paper/2108.13898/) (2021)
- [SocialPET: Socially Informed Pattern Exploiting Training for Few-Shot Stance Detection in Social Media](https://mlsanity.com/paper/2403.05216/) (2024)
- [Keeping in Time: Adding Temporal Context to Sentiment Analysis Models](https://mlsanity.com/paper/2309.13562/) (2023)

## Abstract (arXiv)

Given the rapidly evolving nature of social media and people's views, word usage changes over time. Consequently, the performance of a classifier trained on old textual data can drop dramatically when tested on newer data. While research in stance classification has advanced in recent years, no effort has been invested in making these classifiers have persistent performance over time. To study this phenomenon we introduce two novel large-scale, longitudinal stance datasets. We then evaluate the performance persistence of stance classifiers over time and demonstrate how it decays as the temporal gap between training and testing data increases. We propose a novel approach to mitigate this performance drop, which is based on temporal adaptation of the word embeddings used for training the stance classifier. This enables us to make use of readily available unlabelled data from the current time period instead of expensive annotation efforts. We propose and compare several approaches to embedding adaptation and find that the Incremental Temporal Alignment (ITA) model leads to the best results in reducing performance drop over time.