In affective natural language generation (NLG) a major aim is to be able to influence the emotional effects evoked in the addressee through the intelligent ...
We report on three studies in which texts that gave positive feedback on an IQ test performance were tested for emotional effects on the recipient. The first ...
Jun 30, 2023 · Affective Text: Generation Strategies and Emotion Measurement Issues. June 30, 2023. Authors. Ielka van der Sluis. Chris Mellish.
Original language, English. Title of host publication, Proceedings of the 24th Florida Artificial Intelligence Research Society Conference (FLAIRS-24).
We claim that Affective NLG requires a revision of the generation methods and of the knowledge sources (about the domain and about the Hearer) that are employed ...
This research addresses these challenges and develops better ways to measure emotions in text. Firstly, the subjective passages must undergo preprocessing to ...
Missing: Strategies | Show results with:Strategies
This extensive study categorizes and critically evaluates a spectrum of affect recognition methods, from unimodal to multimodal approaches, including bimodal ...
Conditional natural language generation meth- ods often require either expensive fine-tuning or training a large language model from scratch.
May 23, 2023 · This paper discusses strategies to improve the effectiveness of affective text analysis, the research over how words and sentences correlate to ...
Missing: Measurement Issues.
Feb 21, 2024 · In this paper, we propose the Emotional Chain-of-Thought (ECoT), a plug-and-play prompting method that enhances the performance of LLMs on various emotional ...