In 2001, EU defined Corporate Social Responsibility (CSR) as “a concept whereby companies integrate social and environmental concerns in their business operations and in their interaction with their stakeholders on a voluntary basis. Being socially responsible means not only fulfilling legal expectations, but also going beyond compliance and investing more into human capital, the environment, and the relations with stakeholders”. Following this definition, the CSR’ pillars are represented by environmental, social, and economic sustainability, and must be communicated to the society through appropriate reports. Sentiment Analysis (SA) can capture the tone and opinion of reports by detecting polarity and identifying the class of emotion hidden in the documents. SA can be conducted at different levels: document, sentence and aspect. However, SA depends on the availability of dictionary. This dictionary has a great influence on results and the corresponding analyses. The construction of a universal sentiment dictionary that fits all domains is very complex because word sentiment depends on the domain it has been used for. The dictionaries of given domain cannot easily be applied to other domains because terms can have opposite sentiments when used in different situations. For this reason, we developed a customized lexical- based dictionary for Italian sustainability terms using methods for sentiment polarity categorization based on polarity features, such as adjectives, verbs, and nouns, by combining textual analysis techniques with the properties of social network analysis. The corpus is composed by environmental, social, and governance (ESG) disclosure strategies for Italian listed companies that closed the financial year at 31st December 2021.

SustDict: a customized lexical-based dictionary for CSR., 2022.

SustDict: a customized lexical-based dictionary for CSR.

Zavarrone, Emma;Forciniti, Alessia;Muscariello, Marta
2022-01-01

Abstract

In 2001, EU defined Corporate Social Responsibility (CSR) as “a concept whereby companies integrate social and environmental concerns in their business operations and in their interaction with their stakeholders on a voluntary basis. Being socially responsible means not only fulfilling legal expectations, but also going beyond compliance and investing more into human capital, the environment, and the relations with stakeholders”. Following this definition, the CSR’ pillars are represented by environmental, social, and economic sustainability, and must be communicated to the society through appropriate reports. Sentiment Analysis (SA) can capture the tone and opinion of reports by detecting polarity and identifying the class of emotion hidden in the documents. SA can be conducted at different levels: document, sentence and aspect. However, SA depends on the availability of dictionary. This dictionary has a great influence on results and the corresponding analyses. The construction of a universal sentiment dictionary that fits all domains is very complex because word sentiment depends on the domain it has been used for. The dictionaries of given domain cannot easily be applied to other domains because terms can have opposite sentiments when used in different situations. For this reason, we developed a customized lexical- based dictionary for Italian sustainability terms using methods for sentiment polarity categorization based on polarity features, such as adjectives, verbs, and nouns, by combining textual analysis techniques with the properties of social network analysis. The corpus is composed by environmental, social, and governance (ESG) disclosure strategies for Italian listed companies that closed the financial year at 31st December 2021.
Inglese
2022
16th International Conference on Statistical Analysis of Textual Data (JADT 2022)
Napoli
2022
internazionale
contributo
Proceedings of the 16th International Conference on Statistical Analysis of Textual Data (JADT 2022)
Misuraca, Michelangelo; Scepi, Germana; Spano, Maria
979-12-80153-30-2
VADISTAT Press
esperti anonimi
A stampa
Settore SECS-S/05 - Statistica Sociale
3
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10808/46704
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • ???jsp.display-item.citation.isi??? ND
social impact