• Corpus ID: 212734256

PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry

@inproceedings{Haider2020POEMOCA,
  title={PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry},
  author={T. Haider and Steffen Eger and Evgeny Kim and Roman Klinger and Winfried Menninghaus},
  booktitle={LREC},
  year={2020}
}
Most approaches to emotion analysis of social media, literature, news, and other domains focus exclusively on basic emotion categories as defined by Ekman or Plutchik. However, art (such as literature) enables engagement in a broader range of more complex and subtle emotions. These have been shown to also include mixed emotional responses. We consider emotions in poetry as they are elicited in the reader, rather than what is expressed in the text or intended by the author. Thus, we… 

Figures and Tables from this paper

x-enVENT: A Corpus of Event Descriptions with Experiencer-specific Emotion and Appraisal Annotations
Emotion classification is often formulated as the task to categorize texts into a predefined set of emotion classes. So far, this task has been the recognition of the emotion of writers and readers, as
Emotion-Aware, Emotion-Agnostic, or Automatic: Corpus Creation Strategies to Obtain Cognitive Event Appraisal Annotations
TLDR
This work analyzes two manual annotation settings and evaluates a purely automatic rule-based labeling strategy (inferring appraisal from annotated emotion classes), indicating that it might be possible to automatically create appraisal corpora for every domain for which emotion corpora already exist.
DISCO PAL: Diachronic Spanish Sonnet Corpus with Psychological and Affective Labels
TLDR
This article presents a study over an annotated corpus of Spanish sonnets, in order to analyse if it is possible to build features from their individual words for predicting the General Affective Meaning (GAM) of the text.
Lexico-semantic and affective modelling of Spanish poetry: A semi-supervised learning approach
TLDR
This paper proposes a semi-supervised learning approach for inferring 21 psychological categories evoked by a corpus of 4572 sonnets, along with 10 affective and lexico-semantic multiclass ones and sees that this approach provides an AUC increase of up to 0.12, as opposed to using transformers alone.
Metrical Tagging in the Wild: Building and Annotating Poetry Corpora with Rhythmic Features
TLDR
This work provides large poetry corpora for English and German, and annotate prosodic features in smaller corpora to train corpus driven neural models that enable robust large scale analysis and shows that BiLSTM-CRF models with syllable embeddings outperform a CRF baseline and different BERT-based approaches.
Experiencers, Stimuli, or Targets: Which Semantic Roles Enable Machine Learning to Infer the Emotions?
TLDR
This work trains emotion classification models on five available datasets annotated with at least one semantic role by masking the fillers of these roles in the text in a controlled manner and finds that across multiple corpora, stimuli and targets carry emotion information, while the experiencer might be considered a confounder.
End-to-end style-conditioned poetry generation: What does it take to learn from examples alone?
In this work, we design an end-to-end model for poetry generation based on conditioned recurrent neural network (RNN) language models whose goal is to learn stylistic features (poem length,
Sentiment Analysis of Latin Poetry: First Experiments on the Odes of Horace
TLDR
A small gold standard made of eight poems by Horace is described, in which each sentence is labeled manually for the sentiment using a four-value classification (positive, negative, neutral and mixed), to evaluate two automatic approaches for sentiment classification.
Transformers analyzing poetry: multilingual metrical pattern prediction with transfomer-based language models
TLDR
Despite being initially conceived as models suitable for semantic tasks, transformers-based models retain enough structural information to perform reasonably well for Spanish on a monolingual setting, and outperforms both for English and German when using a model trained on the three languages, showing evidence of the benefits of cross-lingual transfer between the languages.
GUJARATI POETRY CLASSIFICATION BASED ON EMOTIONS USING DEEP LEARNING
TLDR
Study presents a novel perspective in sentiment capture as of Gujarati Poems with the use of variety of characteristic there within Gujarati poems to disclose emotions through Gujarati poetries.
...
...

References

SHOWING 1-10 OF 76 REFERENCES
Who Feels What and Why? Annotation of a Literature Corpus with Semantic Roles of Emotions
TLDR
A publicly available corpus based on Project Gutenberg, REMAN (Relational EMotion ANnotation), manually annotated for spans which correspond to emotion trigger phrases and entities/events in the roles of experiencers, targets, and causes of the emotion is presented.
EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis
TLDR
EmoBank, a corpus of 10k English sentences balancing multiple genres, is described, which is annotated with dimensional emotion metadata in the Valence-Arousal-Dominance (VAD) representation format and achieves close-to-human performance when mapping between dimensional and categorical formats.
An Analysis of Annotated Corpora for Emotion Classification in Text
TLDR
A survey of the datasets is carried out, and a subset of corpora is better classified with models trained on a different corpus, which simplifies the choice of the most appropriate resources for developing a model for a novel domain.
Measuring aesthetic emotions: A review of the literature and a new assessment tool
TLDR
The development of a questionnaire that is applicable across many of these domains: the Aesthetic Emotions Scale (Aesthemos), which contains 21 subscales that are designed to assess the emotional signature of responses to stimuli’s perceived aesthetic appeal in a highly differentiated manner.
Annotation, Modelling and Analysis of Fine-Grained Emotions on a Stance and Sentiment Detection Corpus
TLDR
The SemEval 2016 stance and sentiment dataset is extended with emotion annotation to investigate annotation reliability and annotation merging, and the relation between emotion annotation and the other annotation layers (stance, sentiment).
Emotions from Text: Machine Learning for Text-based Emotion Prediction
TLDR
This paper explores the text-based emotion prediction problem empirically, using supervised machine learning with the SNoW learning architecture to classify the emotional affinity of sentences in the narrative domain of children's fairy tales, for subsequent usage in appropriate expressive rendering of text-to-speech synthesis.
IEST: WASSA-2018 Implicit Emotions Shared Task
TLDR
A shared task where systems have to predict the emotions in a large automatically labeled dataset of tweets without access to words denoting emotions, and is called the Implicit Emotion Shared Task (IEST) because the systems has to infer the emotion mostly from the context.
Readers vs. Writers vs. Texts: Coping with Different Perspectives of Text Understanding in Emotion Annotation
We here examine how different perspectives of understanding written discourse, like the reader’s, the writer’s or the text’s point of view, affect the quality of emotion annotations. We conducted a
Style Detection for Free Verse Poetry from Text and Speech
TLDR
This work presents a model for automatic prosodic classification of spoken free verse poetry that uses deep hierarchical attention networks to integrate the source text and audio and predict the assigned class, and finds that classes can reliably be differentiated.
...
...