Aspect Based Sentiment Analysis of Finnish Neighborhoods: Insights from Suomi24

Laleh Davoodi; Anssi Öörni; Ville Harkke

Aspect Based Sentiment Analysis of Finnish Neighborhoods: Insights from Suomi24

Laleh Davoodi, Anssi Öörni^*, Ville Harkke^*

^*Corresponding author for this work

Research output: Chapter in Book/Conference proceeding › Published conference proceeding › Scientific › peer-review

Abstract

This study presents an approach to Aspect-Based Sentiment Analysis (ABSA) using Natural Language Processing (NLP) techniques to explore public sentiment across 12 suburban neighborhoods in Finland. We employed and compared a range of machine learning models for sentiment classification, with the RoBERTa model emerging as the best performer. Using RoBERTa, we conducted a comprehensive sentiment analysis(SA) on a manually annotated dataset and a predicted dataset comprising 32,183 data points to investigate sentiment trends over time in these areas. The results provide insights into fluctuations in public sentiment, highlighting both the robustness of the RoBERTa model and significant shifts in sentiment for specific neighborhoods over time. This research contributes to a deeper understanding of neighborhood sentiment dynamics in Finland, with potential implications for social research and urban development.

Original language	English
Title of host publication	Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages
Publisher	Association for Computational Linguistics
Pages	1-11
ISBN (Print)	979-8-89176-128-5
Publication status	Published - Dec 2024
MoE publication type	A4 Article in a conference publication
Event	The 9th International Workshop on Computational Linguistics for Uralic Languages - Finland, Helsinki, Finland Duration: 28 Nov 2024 → 29 Nov 2024 Conference number: ISBN 979-8-89176-128-5 https://acl-sigur.github.io/iwclul2024.html

Conference

Conference	The 9th International Workshop on Computational Linguistics for Uralic Languages
Abbreviated title	IWCLUL2024
Country/Territory	Finland
City	Helsinki
Period	28/11/24 → 29/11/24
Internet address	https://acl-sigur.github.io/iwclul2024.html

Keywords

Aspect Based Sentiment Analysis
Finnish Neighborhoods
Suomi24
Machine Learning
Natural Language Processing

Access to Document

https://aclanthology.org/2024.iwclul-1Licence: Publisher rights policy
https://acl-sigur.github.io/iwclul2024Licence: Publisher rights policy
https://aclanthology.org/2024.iwclul-1.pdfLicence: Publisher rights policy

Cite this

@inproceedings{0aaa614ac7b24528981425def2bb0a26,

title = "Aspect Based Sentiment Analysis of Finnish Neighborhoods: Insights from Suomi24",

abstract = "This study presents an approach to Aspect-Based Sentiment Analysis (ABSA) using Natural Language Processing (NLP) techniques to explore public sentiment across 12 suburban neighborhoods in Finland. We employed and compared a range of machine learning models for sentiment classification, with the RoBERTa model emerging as the best performer. Using RoBERTa, we conducted a comprehensive sentiment analysis(SA) on a manually annotated dataset and a predicted dataset comprising 32,183 data points to investigate sentiment trends over time in these areas. The results provide insights into fluctuations in public sentiment, highlighting both the robustness of the RoBERTa model and significant shifts in sentiment for specific neighborhoods over time. This research contributes to a deeper understanding of neighborhood sentiment dynamics in Finland, with potential implications for social research and urban development.",

keywords = "Aspect Based Sentiment Analysis, Finnish Neighborhoods, Suomi24, Machine Learning, Natural Language Processing",

author = "Laleh Davoodi and Anssi {\"O}{\"o}rni and Ville Harkke",

year = "2024",

month = dec,

language = "English",

isbn = "979-8-89176-128-5",

pages = "1--11",

booktitle = "Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "The 9th International Workshop on Computational Linguistics for Uralic Languages, IWCLUL2024 ; Conference date: 28-11-2024 Through 29-11-2024",

url = "https://acl-sigur.github.io/iwclul2024.html",

}

Davoodi, L , Öörni, A & Harkke, V 2024, Aspect Based Sentiment Analysis of Finnish Neighborhoods: Insights from Suomi24. in Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages. Association for Computational Linguistics, pp. 1-11, The 9th International Workshop on Computational Linguistics for Uralic Languages, Helsinki, Finland, 28/11/24. <https://aclanthology.org/2024.iwclul-1>

Aspect Based Sentiment Analysis of Finnish Neighborhoods: Insights from Suomi24. / Davoodi, Laleh ; Öörni, Anssi ; Harkke, Ville.
Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages. Association for Computational Linguistics, 2024. p. 1-11.

Research output: Chapter in Book/Conference proceeding › Published conference proceeding › Scientific › peer-review

TY - GEN

T1 - Aspect Based Sentiment Analysis of Finnish Neighborhoods: Insights from Suomi24

AU - Davoodi, Laleh

AU - Öörni, Anssi

AU - Harkke, Ville

N1 - Conference code: ISBN 979-8-89176-128-5

PY - 2024/12

Y1 - 2024/12

N2 - This study presents an approach to Aspect-Based Sentiment Analysis (ABSA) using Natural Language Processing (NLP) techniques to explore public sentiment across 12 suburban neighborhoods in Finland. We employed and compared a range of machine learning models for sentiment classification, with the RoBERTa model emerging as the best performer. Using RoBERTa, we conducted a comprehensive sentiment analysis(SA) on a manually annotated dataset and a predicted dataset comprising 32,183 data points to investigate sentiment trends over time in these areas. The results provide insights into fluctuations in public sentiment, highlighting both the robustness of the RoBERTa model and significant shifts in sentiment for specific neighborhoods over time. This research contributes to a deeper understanding of neighborhood sentiment dynamics in Finland, with potential implications for social research and urban development.

AB - This study presents an approach to Aspect-Based Sentiment Analysis (ABSA) using Natural Language Processing (NLP) techniques to explore public sentiment across 12 suburban neighborhoods in Finland. We employed and compared a range of machine learning models for sentiment classification, with the RoBERTa model emerging as the best performer. Using RoBERTa, we conducted a comprehensive sentiment analysis(SA) on a manually annotated dataset and a predicted dataset comprising 32,183 data points to investigate sentiment trends over time in these areas. The results provide insights into fluctuations in public sentiment, highlighting both the robustness of the RoBERTa model and significant shifts in sentiment for specific neighborhoods over time. This research contributes to a deeper understanding of neighborhood sentiment dynamics in Finland, with potential implications for social research and urban development.

KW - Aspect Based Sentiment Analysis

KW - Finnish Neighborhoods

KW - Suomi24

KW - Machine Learning

KW - Natural Language Processing

M3 - Published conference proceeding

SN - 979-8-89176-128-5

SP - 1

EP - 11

BT - Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages

PB - Association for Computational Linguistics

T2 - The 9th International Workshop on Computational Linguistics for Uralic Languages

Y2 - 28 November 2024 through 29 November 2024

ER -

Aspect Based Sentiment Analysis of Finnish Neighborhoods: Insights from Suomi24

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this