Figure - uploaded by Hyunwoo Kim
Content may be subject to copyright.
GUI of KOSCA (freely available at https://haerimhwang.github.io/tools/Korean-syntactic-complexity-analyzer)
Source publication
Given the lack of computational tools available for assessing second language (L2) production in Korean, this study introduces a novel automated tool called the Korean Syntactic Complexity Analyzer (KOSCA) for measuring syntactic complexity in L2 Korean production. As an open-source graphic user interface (GUI) developed in Python, KOSCA provides s...
Similar publications
In recent times, companies and institutions globally are increasingly adopting automated systems for recording employee attendance due to the inefficiency and error-prone nature of traditional methods. Face recognition is the fastest, most natural, and most accurate way to identify someone, despite its difficulty. Remote deployment and control of t...
Coronavirus disease (COVID-19) is a major health threat worldwide pandemic, first identified in Malaysia on 25 January 2020. This outbreak can be represented in the mathematical expressions of a non-linear system of ordinary differential equations (ODEs). With the lack of a predictive SEIRD model in terms of Graphical Users Interface (GUI) in Malay...
Raster Forge is a Python library and graphical user interface for raster data manipulation and analysis. The tool is focused on remote sensing applications, particularly in wildfire management. It allows users to import, visualize, and process raster layers for tasks such as image compositing or topographical analysis. For wildfire management, it g...
Circadian rhythms are ubiquitous across the kingdoms of life and serve important roles in regulating physiology and behavior at many levels. These rhythms occur in ~24-hour cycles and are driven by a core molecular oscillator. Circadian timekeeping enables organisms to anticipate daily changes by timing their growth and internal processes. Neurospo...
At the end of every session, level coordinators, departmental, and faculty examination board members in University of Jos, were faced with the challenge of checking each level senate format results to ensure that it conform to the standard set by the University. Some of the items checked includes: Scores and the corresponding grade points, and grad...
Citations
... The availability of advanced natural language processing (NLP) tools has revolutionized the field of writing assessment. A growing number of NLP tools have been developed to account for lexical, syntactic, and discourse-level features in students' written production, with most being centered around the English language (e.g., Brezina & Pallotti, 2019;Crossley et al., 2016Crossley et al., , 2019Graesser et al., 2004;Hwang & Kim, 2023a, 2023bKyle, 2016;Lu, 2010). These NLP tools have been implemented in two strands of research: writing development (e.g., Aparici et al., 2021;Beers & Nagy, 2011;Jisa et al., 2002;Nippold et al., 2005;Staples et al., 2016) and writing quality (e.g., MacArthur et al., 2019;Tate et al., 2024;Wang & Troia, 2023;Wang et al., 2024). ...
... Syntactic proficiency in writing is a multidimensional concept, encompassing syntactic complexity, accuracy, fluency, and appropriateness (Durrant et al., 2021). In line with related NLP studies (e.g., Hwang & Kim, 2023b;Lu, 2010;Vandeweerd, 2021), the current study will examine two aspects of syntactic proficiency: syntactic complexity and fluency to facilitate comparisons with prior research. Syntactic complexity refers to the sophistication and variety of syntactic structures in the written text (Crossley, 2020;Ortega, 2003), and syntactic fluency relates to the production rate of syntactic structures within a specific period of time (Wolfe-Quintero et al., 1998). ...
... NLP tools measuring syntactic features utilize one of two main units of analysis: sentences (e.g., Hwang & Kim, 2023b) or T-units (e.g., Kyle, 2016). ARSA implements a sentence-based analysis because sentences represent the highest possible syntactic unit in a written text (Biber et al., 1999;Quirk et al., 1985), and can be identified more reliably in Arabic texts based on writer-produced punctuation marks (periods, exclamation marks, and question marks). ...
Research on the linguistic features of Arabic texts is scarce due to the limited resources available for the Arabic language. To address this issue, the present study introduces the Arabic syntactic analyzer (ARSA), a freely available command-line interface tool that is easy to use and involves nine syntactic complexity indices and four syntactic fluency indices. The validity of ARSA was tested by investigating the extent to which each of its indices could predict expert judgments of essay quality. Linear regression models revealed that five ARSA indices positively predicted expert ratings of Arabic essays. The stepwise multiple regression model indicated that three of the ARSA indices explained 23.0% of the total variance in writing quality. These results indicate that ARSA has some predictive validity in accounting for Arabic writing quality. Comparing our results to prior English research, we also observed some cross-linguistic variation in the relationship between syntactic complexity and writing quality. The introduction of ARSA has the potential to increase research on Arabic writing and broaden the scope of writing research.
... On the other hand, instrument validity examines the tool's ability to accurately capture and predict the target linguistic effect it was designed to measure (e.g., Hwang & Kim, 2023). This aspect of validation ensures that the tool fulfills its intended purpose. ...
The majority of neighborhood calculators are restricted to one language. The limited availability of multilingual neighborhood calculators could pose challenges for conducting psycholinguistic research on low-resource languages. Therefore, this study introduced Jiwar, a database and calculator for neighborhood information across three levels (orthographic, phonological, and phonographic) across 40 languages. The database contains information for 24 linguistic and neighborhood measures, while the Python-based calculator allows users to compute more than 46 neighborhood measures for words and nonwords. This study further examined the Jiwar calculator’s instrument reliability and validity. Correlations with previous datasets across several languages suggested the strong reliability of two key Jiwar measures. Multiple-linear regression models revealed that a subset of Jiwar measures significantly predicted behavioral results in lexical decision and visual naming tasks, indicating the validity of the Jiwar calculator. Jiwar is an open-source, Python-based tool that is designed to expand to more languages and functions.
