Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing

App reviews in mobile app stores contain useful information which is used to improve applications and promote software evolution. This information is processed by automatic tools which prioritize reviews. In order to carry out this prioritization, reviews are decomposed into features like category a...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Rojas Paredes, Andrés, Mareco, Brenda
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2024
Materias:
Ciencias Informáticas
app reviews
user feedback processing
weighted function
pipeline
digits precision
algorithmic bias
feature extraction
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/176523
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-176523
record_format dspace
spelling I19-R120-10915-1765232025-02-14T20:10:09Z http://sedici.unlp.edu.ar/handle/10915/176523 Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing Rojas Paredes, Andrés Mareco, Brenda 2024-10 2024 2025-02-14T14:52:38Z en Ciencias Informáticas app reviews user feedback processing weighted function pipeline digits precision algorithmic bias feature extraction App reviews in mobile app stores contain useful information which is used to improve applications and promote software evolution. This information is processed by automatic tools which prioritize reviews. In order to carry out this prioritization, reviews are decomposed into features like category and sentiment. Then, a weighted function assigns a weight to each feature and a review ranking is calculated. Unfortunately, in order to extract category and sentiment from reviews, its is required at least a classifier trained in an annotated corpus. Therefore this task is computational demanding. Thus, in this work, we propose Shannon Entropy as a simple feature which can replace standard features. Our results show that a Shannon Entropy based ranking is better than a standard ranking according to the NDCG metric. This result is promising even if we require fairness by means of algorithmic bias. Finally, we highlight a computational limit which appears in the search of the best ranking. Red de Universidades con Carreras en Informática Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 772-781
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
app reviews
user feedback processing
weighted function
pipeline
digits precision
algorithmic bias
feature extraction
spellingShingle Ciencias Informáticas
app reviews
user feedback processing
weighted function
pipeline
digits precision
algorithmic bias
feature extraction
Rojas Paredes, Andrés
Mareco, Brenda
Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing
topic_facet Ciencias Informáticas
app reviews
user feedback processing
weighted function
pipeline
digits precision
algorithmic bias
feature extraction
description App reviews in mobile app stores contain useful information which is used to improve applications and promote software evolution. This information is processed by automatic tools which prioritize reviews. In order to carry out this prioritization, reviews are decomposed into features like category and sentiment. Then, a weighted function assigns a weight to each feature and a review ranking is calculated. Unfortunately, in order to extract category and sentiment from reviews, its is required at least a classifier trained in an annotated corpus. Therefore this task is computational demanding. Thus, in this work, we propose Shannon Entropy as a simple feature which can replace standard features. Our results show that a Shannon Entropy based ranking is better than a standard ranking according to the NDCG metric. This result is promising even if we require fairness by means of algorithmic bias. Finally, we highlight a computational limit which appears in the search of the best ranking.
format Objeto de conferencia
Objeto de conferencia
author Rojas Paredes, Andrés
Mareco, Brenda
author_facet Rojas Paredes, Andrés
Mareco, Brenda
author_sort Rojas Paredes, Andrés
title Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing
title_short Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing
title_full Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing
title_fullStr Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing
title_full_unstemmed Shannon Entropy is better Feature than Category and Sentiment in User Feedback Processing
title_sort shannon entropy is better feature than category and sentiment in user feedback processing
publishDate 2024
url http://sedici.unlp.edu.ar/handle/10915/176523
work_keys_str_mv AT rojasparedesandres shannonentropyisbetterfeaturethancategoryandsentimentinuserfeedbackprocessing
AT marecobrenda shannonentropyisbetterfeaturethancategoryandsentimentinuserfeedbackprocessing
_version_ 1845116790213967872

Ejemplares similares