@inproceedings{gopalakrishna-pillai-etal-2025-engagement,
title = "Engagement-driven Persona Prompting for Rewriting News Tweets",
author = "Gopalakrishna Pillai, Reshmi and
Fokkens, Antske and
van Atteveldt, Wouter",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.576/",
pages = "8612--8622",
abstract = "Text style transfer is a challenging research task which modifies the linguistic style of a given text to meet pre-set objectives such as making the text simpler or more accessible. Though large language models have been found to give promising results, text rewriting to improve audience engagement of social media content is vastly unexplored. Our research investigates the performance of various prompting strategies in the task of rewriting Dutch news tweets in specific linguistic styles (formal, casual and factual). Apart from zero-shot and few-shot prompting variants, with and without personas, we also explore prompting with feedback on predicted engagement. We perform an extensive analysis of 18 different combinations of Large Language Models (GPT-3.5, GPT-4, Mistral-7B) and prompting strategies on three different metrics: ROUGE-L, semantic similarity and predicted engagement. We find that GPT-4 with feedback and persona prompting performs the best in terms of predicted engagement for all three language styles. Our results motivate further application of usage of prompting techniques to rewrite news headlines on Twitter to align with specific style guidelines."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gopalakrishna-pillai-etal-2025-engagement">
<titleInfo>
<title>Engagement-driven Persona Prompting for Rewriting News Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reshmi</namePart>
<namePart type="family">Gopalakrishna Pillai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antske</namePart>
<namePart type="family">Fokkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wouter</namePart>
<namePart type="family">van Atteveldt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text style transfer is a challenging research task which modifies the linguistic style of a given text to meet pre-set objectives such as making the text simpler or more accessible. Though large language models have been found to give promising results, text rewriting to improve audience engagement of social media content is vastly unexplored. Our research investigates the performance of various prompting strategies in the task of rewriting Dutch news tweets in specific linguistic styles (formal, casual and factual). Apart from zero-shot and few-shot prompting variants, with and without personas, we also explore prompting with feedback on predicted engagement. We perform an extensive analysis of 18 different combinations of Large Language Models (GPT-3.5, GPT-4, Mistral-7B) and prompting strategies on three different metrics: ROUGE-L, semantic similarity and predicted engagement. We find that GPT-4 with feedback and persona prompting performs the best in terms of predicted engagement for all three language styles. Our results motivate further application of usage of prompting techniques to rewrite news headlines on Twitter to align with specific style guidelines.</abstract>
<identifier type="citekey">gopalakrishna-pillai-etal-2025-engagement</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.576/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8612</start>
<end>8622</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Engagement-driven Persona Prompting for Rewriting News Tweets
%A Gopalakrishna Pillai, Reshmi
%A Fokkens, Antske
%A van Atteveldt, Wouter
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F gopalakrishna-pillai-etal-2025-engagement
%X Text style transfer is a challenging research task which modifies the linguistic style of a given text to meet pre-set objectives such as making the text simpler or more accessible. Though large language models have been found to give promising results, text rewriting to improve audience engagement of social media content is vastly unexplored. Our research investigates the performance of various prompting strategies in the task of rewriting Dutch news tweets in specific linguistic styles (formal, casual and factual). Apart from zero-shot and few-shot prompting variants, with and without personas, we also explore prompting with feedback on predicted engagement. We perform an extensive analysis of 18 different combinations of Large Language Models (GPT-3.5, GPT-4, Mistral-7B) and prompting strategies on three different metrics: ROUGE-L, semantic similarity and predicted engagement. We find that GPT-4 with feedback and persona prompting performs the best in terms of predicted engagement for all three language styles. Our results motivate further application of usage of prompting techniques to rewrite news headlines on Twitter to align with specific style guidelines.
%U https://aclanthology.org/2025.coling-main.576/
%P 8612-8622
Markdown (Informal)
[Engagement-driven Persona Prompting for Rewriting News Tweets](https://aclanthology.org/2025.coling-main.576/) (Gopalakrishna Pillai et al., COLING 2025)
ACL