Assessing and improving academic writing skills is a crucial component of higher education. To support students in this endeavor, a comprehensive self-assessment toolkit was developed to provide personalized feedback and guide their writing improvement. The current study aimed to rigorously evaluate the validity and reliability of this academic writing self-assessment toolkit. The development and validation of the academic writing self-assessment toolkit involved several key steps. First, a thorough review of the literature was conducted to identify the essential criteria for authentic assessment. Next, an analysis of medical students' reflection papers was undertaken to gain insights into their experiences using AI-powered tools for writing feedback. Based on these initial steps, a preliminary version of the self-assessment toolkit was devised. An expert focus group discussion was then convened to refine the questions and content of the toolkit. To assess content validity, the toolkit was evaluated by a panel of 22 medical student participants. They were asked to review each item and provide feedback on the relevance and comprehensiveness of the toolkit for evaluating academic writing skills. Face validity was also examined, with the students assessing the clarity, wording, and appropriateness of the toolkit items. The content validity evaluation revealed that 95% of the toolkit items were rated as highly relevant, and 88% were deemed comprehensive in assessing key aspects of academic writing. Minor wording changes were suggested by the students to enhance clarity and interpretability. The face validity assessment found that 92% of the items were rated as unambiguous, with 90% considered appropriate and relevant for self-assessment. Feedback from the students led to the refinement of a few items to improve their clarity in the context of the Persian language. The robust reliability testing demonstrated the consistency and stability of the academic writing self-assessment toolkit in measuring students' writing skills over time. The comprehensive evaluation process has established the academic writing self-assessment toolkit as a robust and credible instrument for supporting students' writing improvement. The toolkit's strong psychometric properties and user-centered design make it a valuable resource for enhancing academic writing skills in higher education.
This study explores the potential impact of ChatGPT on the academic writing skills development of medical students enrolled in a compulsory 3-unit writing course at a medical university. The research focuses on two primary objectives, which are formulated as two research questions: Firstly, does the use of ChatGPT enhance medical students’ English academic writing skills compared to conventional writing training? Secondly, how does the use of ChatGPT impact on different components of academic writing? A longitudinal intervention design was employed with 83 participants from two writing classes in the experimental and control groups. The findings demonstrated ChatGPT’s significant impact on enhancing medical students’ English academic writing skills, with large effect sizes. ChatGPT enhanced students’ writing skills, especially content, organization, vocabulary, and mechanics in the experimental group, while its impact on language use is limited. AI tools like ChatGPT can be valuable in assisting with certain aspects of writing, but they should not be considered a one-size-fits-all solution for enhancing writing skills. The result of the study can be beneficial for educators, particularly those interested in teaching writing.
1 November 2013 in International Journal of Applied Linguistics and English Literature
This study aims to find out the various strategies used in learning vocabularies among Iranian EFL learners in three different proficiency levels (beginner, intermediate and advanced) in Zanjan province. The vocabulary learning strategies which have been used in this research include determination, social, memory, cognitive, and meta-cognitive which follow Schmitt’s taxonomy. 110 students were randomly selected from two language institutes in Zanjan. Schmitt’s (1997) Vocabulary Learning Strategies’ questionnaire was administered to the learners with three proficiency levels. Then, descriptive statistics and Anova were utilized to analyze the data. Descriptive statistics revealed that the participants of the study regardless of their proficiency levels were generally medium strategy users who used all these strategies moderately except for the determination strategies that were used in high level. In addition, basic learners used all different types of strategies more frequently than intermediate and advanced learners. By comparing two other proficiency levels, advanced learners used determination strategies and meta-cognitive strategies more frequently than intermediate learners, while social, memory and cognitive strategies were used more frequently by Intermediates. In order to perceive if the results were statistically significant, Anova for between group mean differences was conducted. It revealed the fact that there is no significant difference among learners with different proficiency levels in application of determination and meta-cognitive strategies while the learners with lower proficiency level used social, memory and cognitive strategies more frequently, that is, these three strategies were used more frequently by basic, intermediate and advanced learners respectively. Keywords: Vocabulary learning strategies, Language learning strategies, Vocabulary learning strategy questionnaire
This corpus-based cross-disciplinary study investigated the syntactic structures and rhetorical combinations of 200 research article titles in two disciplines, namely, medicine (100) and applied linguistics (100). The RA titles were selected from four reputable Iranian English journals. The authors were all Iranian researchers in these two disciplines. The titles were analyzed in light of Dietz taxonomy. First, the frequencies and percentages of each syntactic and rhetorical construction occurrence have been calculated. Next, the authors performed a t-test regarding title length and the chi-square test to decide whether syntactic or rhetorical construction is a discipline-specific convention. The findings revealed thatmedical titles were longer than the linguistic ones. The frequency and percentage of both single- and multi-unit RA titles were essentially the same in both disciplines. Concerning the syntactic components of single-unit RA titles, the most frequently used structure was the nominal construction, followed by verbal and prepositional ones. The most recurrent syntactic components of the nominal structure in both disciplines were post- and pre-modified, with medical titles overtaking the linguistic titles in all nominal categories. In terms of verbal constructions, the dominant structure in medicine was the full sentence, and in applied linguistics, gerund phrases. Regarding the rhetorical components of multi-unit RA titles, medical titles took precedence over the linguistic titles in using the topic method. The topic scope and topic description organization are mostly reported in applied linguistics titles. In this study, however, two new rhetorical combinations were identified. The chi-square test results only confirmed the verbal structures of single-unit and the rhetorical combinations of multi-unit RA titles as distinctive features for each discipline.