# Learning Stance Embeddings from Signed Social Graphs

arXiv: https://arxiv.org/abs/2201.11675 · HTML: https://mlsanity.com/paper/2201.11675/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 43 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 16 of 16)

- [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)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [LINE: Large-scale Information Network Embedding](https://mlsanity.com/paper/1503.03578/) (2015)
- [Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec](https://mlsanity.com/paper/1710.02971/) (2017)
- [Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations](https://mlsanity.com/paper/2010.03640/) (2020)
- [Adversarial Learning for Zero-Shot Stance Detection on Social Media](https://mlsanity.com/paper/2105.06603/) (2021)
- [Exploiting Social Network Structure for Person-to-Person Sentiment Analysis](https://mlsanity.com/paper/1409.2450/) (2014)
- [SNE: Signed Network Embedding](https://mlsanity.com/paper/1703.04837/) (2017)
- [Distributed Representations of Signed Networks](https://mlsanity.com/paper/1702.06819/) (2017)
- [POLE: Polarized Embedding for Signed Networks](https://mlsanity.com/paper/2110.09899/) (2021)
- [Community-Based Fact-Checking on Twitter's Birdwatch Platform](https://mlsanity.com/paper/2104.07175/) (2021)
- [Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path](https://mlsanity.com/paper/2106.09923/) (2021)
- [Learning Ideological Embeddings from Information Cascades](https://mlsanity.com/paper/2109.13589/) (2021)
- [Applications of Structural Balance in Signed Social Networks](https://mlsanity.com/paper/1402.6865/) (2014)

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

- [NTULM: Enriching Social Media Text Representations with Non-Textual Units](https://mlsanity.com/paper/2210.16586/) (2022)
- [Decoding Climate Disagreement: A Graph Neural Network-Based Approach to Understanding Social Media Dynamics](https://mlsanity.com/paper/2407.07038/) (2024)
- [Signed graphs in data sciences via communicability geometry](https://mlsanity.com/paper/2403.07493/) (2024)
- [Strong and Weak Random Walks on Signed Networks](https://mlsanity.com/paper/2406.08034/) (2024)
- [A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Information](https://mlsanity.com/paper/2411.06855/) (2024)
- [Graph-Based Floor Separation Using Node Embeddings and Clustering of WiFi Trajectories](https://mlsanity.com/paper/2505.08088/) (2025)
- [Adversarial Signed Graph Learning with Differential Privacy](https://mlsanity.com/paper/2512.00307/) (2025)
- [POLAR:A Per-User Association Test in Embedding Space](https://mlsanity.com/paper/2603.15950/) (2026)

## Abstract (arXiv)

A key challenge in social network analysis is understanding the position, or stance, of people in the graph on a large set of topics. While past work has modeled (dis)agreement in social networks using signed graphs, these approaches have not modeled agreement patterns across a range of correlated topics. For instance, disagreement on one topic may make disagreement(or agreement) more likely for related topics. We propose the Stance Embeddings Model(SEM), which jointly learns embeddings for each user and topic in signed social graphs with distinct edge types for each topic. By jointly learning user and topic embeddings, SEM is able to perform cold-start topic stance detection, predicting the stance of a user on topics for which we have not observed their engagement. We demonstrate the effectiveness of SEM using two large-scale Twitter signed graph datasets we open-source. One dataset, TwitterSG, labels (dis)agreements using engagements between users via tweets to derive topic-informed, signed edges. The other, BirdwatchSG, leverages community reports on misinformation and misleading content. On TwitterSG and BirdwatchSG, SEM shows a 39% and 26% error reduction respectively against strong baselines.