diff --git a/paper/paper.md b/paper/paper.md index 6d1a07a..8fd29ae 100644 --- a/paper/paper.md +++ b/paper/paper.md @@ -56,7 +56,7 @@ bibliography: paper.bib Sustainability is an important topic in contemporary discourse. However, the delineation and interpretation of this concept are often different across disciplines [@Salas-Zapata_RĂ­os-Osorio_Cardona-Arias_2017], which hinders effective communication, causes inconsistencies in research and practice, and impedes measurable actions to achieve sustainability [@Waseem_Kota_2017; @Yamada_Kanoi_Koh_Lim_Dove_2022]. With the increasing popularity of text-based assessments [@Amini_Bienstock_Narcum_2018; @Olsen_Fenhann_2008; @Singh_Meena_Khandelwal_Dangayach_2023], these issues have become more prominent, as the criteria vary for evaluating sustainability commitments and contributions. -`seesus`, based on the United Nations (UN) Sustainable Development Goals (SDGs), addresses the critical need in text analysis to capture the concept of sustainability with a rigorous and credible definition. The SDGs provide an international framework and a shared understanding of what it means to be sustainable, balancing the environmental, economic, and social dimensions of sustainability [@UN_2015]. `seesus` identifies expressions regarding achieving the 17 SDGs and their associated 169 targets within a text and labels whether the expressions pertain to social, environmental, or economic sustainability. Unlike other SDG text-mining packages, it is designed to identify not only terms related to the SDGs but also the attainment of SDGs. +`seesus`, based on the United Nations (UN) Sustainable Development Goals (SDGs), addresses the critical need in text analysis to capture the concept of sustainability with a rigorous and credible definition. The SDGs provide an international framework and a shared understanding of what it means to be sustainable, balancing the environmental, economic, and social dimensions of sustainability [@UN_2015]. Automated text analysis to align and classify statements according to the SDGs can help identify the focal points for sustainable development strategies and facilitate data-driven decision-making processes in pursuit of the SDGs. `seesus` identifies expressions regarding achieving the 17 SDGs and their associated 169 targets within a text and labels whether the expressions pertain to social, environmental, or economic sustainability. Unlike other SDG text-mining packages, it is designed to identify not only terms related to the SDGs but also the attainment of SDGs. `seesus` achieves an accuracy rate of 75.5%, as determined by alignment with manual coding. Detailed information on the accuracy evaluation and manual refinement can be found in `SDGdetector` [@Li_Frans_Song_Cai_Zhang_Liu_2023], our R package employing the same matching logic as `seesus`. In an era of large language models, `seesus` chooses to use predefined regular expression patterns instead of machine learning for text classification, because this method is more transparent, replicable, and controllable. Users of `seesus` can examine the matching logic and customize the syntax if necessary. In addition, compared to other text classifiers based on the SDGs in Python, including `SDG-Classifier` [@Rawat_2022], `SDG Auto Labeller` [@Glass_2020], `UN-SDG-Classifier` [@Lamichaney_2021], `EUR-SDG-Mapper` [@Jelicic_van_der_Vorst_Ranjbar_Mijnhardt_2022], `seesus` is the only one that covers all the SDGs and is fine-tuned to the target level. @@ -64,7 +64,7 @@ Given the interdisciplinary nature of the sustainability concept, the usage of t # Functionality -`seesus` currently has four main functions: (1) evaluating whether a statement aligns with the concept of sustainability; (2) identifying SDGs and associated targets in a statement; (3) classifying a statement into social, environmental, and economic sustainability; (4) examining and customizing match syntax. +`seesus` currently has four main functions: (1) evaluating whether a statement aligns with the concept of sustainability; (2) identifying SDGs and associated targets in a statement; (3) classifying a statement into social, environmental, and economic sustainability; (4) customizing match syntax. # Acknowledgements