@inproceedings{achmann-denkler-etal-2026-mobilize,
title = "Mobilize, Inform, Interact: Classifying Political Calls-to-Action Types on {I}nstagram",
author = "Achmann-Denkler, Michael and
Helmig, Clara and
Fehle, Jakob and
Haim, Mario and
Wolff, Christian",
editor = "Afli, Haithem and
Bouamor, Houda and
Zaghouani, Wajdi and
Ghannay, Sahar and
Hossain, Shehenaz",
booktitle = "Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences ({P}olitical{NLP} 2026)",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.politicalnlp-1.14/",
doi = "10.63317/4jqe5mnxo2cc",
pages = "131--138",
abstract = "Calls-to-action (CTAs) are central to digital campaigning, yet computational research has largely focused on binary detection only. We address CTA type classification in German Instagram campaign texts (posts and ephemeral stories), distinguishing Support, Inform, Interact, and No CTA. With limited annotated data, we benchmark a fine-tuned GBERT model against GPT models using zero-shot, few-shot, and retrieval-augmented few-shot prompting in a multi-label setup. Both approaches reach similar performance in five-fold cross-validation (macro-F1 ca. 0.79), with persistent difficulty on the rare Interact category. As a proof of concept, we apply the selected setup to the 2021 federal election corpus and show that parties varied not only in overall CTA use but also in how they balanced appeals across posts versus stories. The results demonstrate the feasibility of CTA type classification with modest data and position retrieval-augmented prompting as a practical alternative to supervised fine-tuning."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="achmann-denkler-etal-2026-mobilize">
<titleInfo>
<title>Mobilize, Inform, Interact: Classifying Political Calls-to-Action Types on Instagram</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Achmann-Denkler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clara</namePart>
<namePart type="family">Helmig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Fehle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Haim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Wolff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haithem</namePart>
<namePart type="family">Afli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Ghannay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shehenaz</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Calls-to-action (CTAs) are central to digital campaigning, yet computational research has largely focused on binary detection only. We address CTA type classification in German Instagram campaign texts (posts and ephemeral stories), distinguishing Support, Inform, Interact, and No CTA. With limited annotated data, we benchmark a fine-tuned GBERT model against GPT models using zero-shot, few-shot, and retrieval-augmented few-shot prompting in a multi-label setup. Both approaches reach similar performance in five-fold cross-validation (macro-F1 ca. 0.79), with persistent difficulty on the rare Interact category. As a proof of concept, we apply the selected setup to the 2021 federal election corpus and show that parties varied not only in overall CTA use but also in how they balanced appeals across posts versus stories. The results demonstrate the feasibility of CTA type classification with modest data and position retrieval-augmented prompting as a practical alternative to supervised fine-tuning.</abstract>
<identifier type="citekey">achmann-denkler-etal-2026-mobilize</identifier>
<identifier type="doi">10.63317/4jqe5mnxo2cc</identifier>
<location>
<url>https://aclanthology.org/2026.politicalnlp-1.14/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>131</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mobilize, Inform, Interact: Classifying Political Calls-to-Action Types on Instagram
%A Achmann-Denkler, Michael
%A Helmig, Clara
%A Fehle, Jakob
%A Haim, Mario
%A Wolff, Christian
%Y Afli, Haithem
%Y Bouamor, Houda
%Y Zaghouani, Wajdi
%Y Ghannay, Sahar
%Y Hossain, Shehenaz
%S Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F achmann-denkler-etal-2026-mobilize
%X Calls-to-action (CTAs) are central to digital campaigning, yet computational research has largely focused on binary detection only. We address CTA type classification in German Instagram campaign texts (posts and ephemeral stories), distinguishing Support, Inform, Interact, and No CTA. With limited annotated data, we benchmark a fine-tuned GBERT model against GPT models using zero-shot, few-shot, and retrieval-augmented few-shot prompting in a multi-label setup. Both approaches reach similar performance in five-fold cross-validation (macro-F1 ca. 0.79), with persistent difficulty on the rare Interact category. As a proof of concept, we apply the selected setup to the 2021 federal election corpus and show that parties varied not only in overall CTA use but also in how they balanced appeals across posts versus stories. The results demonstrate the feasibility of CTA type classification with modest data and position retrieval-augmented prompting as a practical alternative to supervised fine-tuning.
%R 10.63317/4jqe5mnxo2cc
%U https://aclanthology.org/2026.politicalnlp-1.14/
%U https://doi.org/10.63317/4jqe5mnxo2cc
%P 131-138
Markdown (Informal)
[Mobilize, Inform, Interact: Classifying Political Calls-to-Action Types on Instagram](https://aclanthology.org/2026.politicalnlp-1.14/) (Achmann-Denkler et al., PoliticalNLP 2026)
ACL