Capturing Stance Dynamics in Social Media: Open Challenges and Research Directions

Alkhalifa, Rabab; Zubiaga, Arkaitz

doi:10.48550/arxiv.2109.00475

Cited by 1 publication

(2 citation statements)

References 76 publications

(135 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Joe Biden). Our research differs from this body of work in that we aim to (1) investigate the impact of time in stance classification for a particular target, and to (2) propose a model that makes this longitudinal tracking of stance more robust to changes in opinion [8,25] and language [3], and hence more stable in performance. A line of research in stance identification has looked at the evolving nature of stance in rumour conversations [15,31], however this work focuses on stance exchanges in temporally brief conversations, rather than longitudinal persistence of models.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Opinions are Made to be Changed

Alkhalifa

Kochkina

Zubiaga

2021

Proceedings of the 2021 Workshop on Open Challenges in Online Social Networks

View full text Add to dashboard Cite

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. CCS CONCEPTS• Computing methodologies → Natural language processing; Semi-supervised learning; Neural networks.

show abstract

Section: Related Workmentioning

confidence: 99%

“…and people's views change over time [2,10]. This can have an impact on stance classification in social media as the data used for training may not generalise well to future data with different patterns.…”

mentioning

confidence: 99%