Predicting literary quality and reader appreciation of narrative texts are highly complex challenges in quantitative and computational literary studies due to the fluid definitions of quality and the vast feature space that can be considered when modeling a literary work. This paper investigates the potential of sentiment arcs combined with topical-semantic profiling of literary narratives as indicators for their literary quality. Our experiments focus on a large corpus of 19th and 20the century English language literary fiction, using GoodReads' ratings as an imperfect approximation of the diverse range of reader evaluations and preferences. By leveraging a stacked ensemble of regression models, we achieve a promising performance in predicting average readers' scores, indicating the potential of our approach in modeling literary quality.
Description
Modeling Readers’ Appreciation of Literary Narratives Through Sentiment Arcs and Semantic Profiles - ACL Anthology
%0 Conference Paper
%1 moreira2023modeling
%A Moreira, Pascale
%A Bizzoni, Yuri
%A Nielbo, Kristoffer
%A Lassen, Ida Marie
%A Thomsen, Mads
%B Proceedings of the The 5th Workshop on Narrative Understanding
%C Toronto, Canada
%D 2023
%E Akoury, Nader
%E Clark, Elizabeth
%E Iyyer, Mohit
%E Chaturvedi, Snigdha
%E Brahman, Faeze
%E Chandu, Khyathi
%I Association for Computational Linguistics
%K chicago collection corpus dh literature sentiment text
%P 25--35
%R 10.18653/v1/2023.wnu-1.5
%T Modeling Readers' Appreciation of Literary Narratives Through Sentiment Arcs and Semantic Profiles
%U https://aclanthology.org/2023.wnu-1.5
%X Predicting literary quality and reader appreciation of narrative texts are highly complex challenges in quantitative and computational literary studies due to the fluid definitions of quality and the vast feature space that can be considered when modeling a literary work. This paper investigates the potential of sentiment arcs combined with topical-semantic profiling of literary narratives as indicators for their literary quality. Our experiments focus on a large corpus of 19th and 20the century English language literary fiction, using GoodReads' ratings as an imperfect approximation of the diverse range of reader evaluations and preferences. By leveraging a stacked ensemble of regression models, we achieve a promising performance in predicting average readers' scores, indicating the potential of our approach in modeling literary quality.
@inproceedings{moreira2023modeling,
abstract = {Predicting literary quality and reader appreciation of narrative texts are highly complex challenges in quantitative and computational literary studies due to the fluid definitions of quality and the vast feature space that can be considered when modeling a literary work. This paper investigates the potential of sentiment arcs combined with topical-semantic profiling of literary narratives as indicators for their literary quality. Our experiments focus on a large corpus of 19th and 20the century English language literary fiction, using GoodReads{'} ratings as an imperfect approximation of the diverse range of reader evaluations and preferences. By leveraging a stacked ensemble of regression models, we achieve a promising performance in predicting average readers{'} scores, indicating the potential of our approach in modeling literary quality.},
added-at = {2024-03-13T16:50:55.000+0100},
address = {Toronto, Canada},
author = {Moreira, Pascale and Bizzoni, Yuri and Nielbo, Kristoffer and Lassen, Ida Marie and Thomsen, Mads},
biburl = {https://www.bibsonomy.org/bibtex/25cc8dcedb6be5b8672250cd8a0bc37aa/jaeschke},
booktitle = {Proceedings of the The 5th Workshop on Narrative Understanding},
description = {Modeling Readers’ Appreciation of Literary Narratives Through Sentiment Arcs and Semantic Profiles - ACL Anthology},
doi = {10.18653/v1/2023.wnu-1.5},
editor = {Akoury, Nader and Clark, Elizabeth and Iyyer, Mohit and Chaturvedi, Snigdha and Brahman, Faeze and Chandu, Khyathi},
interhash = {c84c7c14e00ef9135d919cdce1462061},
intrahash = {5cc8dcedb6be5b8672250cd8a0bc37aa},
keywords = {chicago collection corpus dh literature sentiment text},
month = jul,
pages = {25--35},
publisher = {Association for Computational Linguistics},
timestamp = {2024-03-13T16:50:55.000+0100},
title = {Modeling Readers{'} Appreciation of Literary Narratives Through Sentiment Arcs and Semantic Profiles},
url = {https://aclanthology.org/2023.wnu-1.5},
year = 2023
}