Stance detection on social media: State of the art and trends

A AlDayel, W Magdy - Information Processing & Management, 2021 - Elsevier
Stance detection on social media is an emerging opinion mining paradigm for various social
and political applications in which sentiment analysis may be sub-optimal. There has been a …

[HTML][HTML] Empirical evaluation of pre-trained transformers for human-level NLP: The role of sample size and dimensionality

AV Ganesan, M Matero, AR Ravula, H Vu… - Proceedings of the …, 2021 - ncbi.nlm.nih.gov
In human-level NLP tasks, such as predicting mental health, personality, or demographics,
the number of observations is often smaller than the standard 768+ hidden state sizes of …

Human language modeling

N Soni, M Matero, N Balasubramanian… - arxiv preprint arxiv …, 2022 - arxiv.org
Natural language is generated by people, yet traditional language modeling views words or
documents as if generated independently. Here, we propose human language modeling …

MeLT: Message-level transformer with masked document representations as pre-training for stance detection

M Matero, N Soni, N Balasubramanian… - arxiv preprint arxiv …, 2021 - arxiv.org
Much of natural language processing is focused on leveraging large capacity language
models, typically trained over single messages with a task of predicting one or more tokens …

[HTML][HTML] Replicable semi-supervised approaches to state-of-the-art stance detection of tweets

M Reveilhac, G Schneider - Information Processing & Management, 2023 - Elsevier
Stance is defined as the expression of a speaker's standpoint towards a given target or
entity. To date, the most reliable method for measuring stance is opinion surveys. However …

Language as a fingerprint: Self-supervised learning of user encodings using transformers

R Rocca, T Yarkoni - Findings of the Association for …, 2022 - aclanthology.org
The way we talk carries information about who we are. Demographics, personality, clinical
conditions, political preferences influence what we speak about and how, suggesting that …

The subtle language of exclusion: Identifying the Toxic Speech of Trans-exclusionary Radical Feminists

C Lu, D Jurgens - Proceedings of the sixth workshop on online …, 2022 - aclanthology.org
Toxic language can take many forms, from explicit hate speech to more subtle
microaggressions. Within this space, models identifying transphobic language have largely …

[PDF][PDF] Characterizing social spambots by their human traits

S Giorgi, L Ungar, HA Schwartz - Findings of the Association for …, 2021 - aclanthology.org
Social spambots, an emerging class of spammers attempting to emulate people, are difficult
for both human annotators and classic bot detection techniques to reliably distinguish from …

Large human language models: A need and the challenges

N Soni, HA Schwartz, J Sedoc… - arxiv preprint arxiv …, 2023 - arxiv.org
As research in human-centered NLP advances, there is a growing recognition of the
importance of incorporating human and social factors into NLP models. At the same time …

LMSOC: An approach for socially sensitive pretraining

V Kulkarni, S Mishra, A Haghighi - arxiv preprint arxiv:2110.10319, 2021 - arxiv.org
While large-scale pretrained language models have been shown to learn effective linguistic
representations for many NLP tasks, there remain many real-world contextual aspects of …