Support Tool Research Articles

Effectiveness of chatbots in improving learning experience in an online course

ABSTRACT This study analyzes the effectiveness of a chatbot in enhancing online learning, addressing the lack of support in traditional online courses. Two questionnaires were administered to participants, providing qualitative data on various aspects of the learning experience. The first questionnaire measured satisfaction, engagement, self-regulation and usefulness in three different groups of participants. The second questionnaire included open-ended questions and Likert scale items, gathering qualitative feedback and perceptions specifically from the group that used the chatbot. Additionally, this study incorporates quantitative analysis to evaluate the chatbot's impact on learning outcomes and student engagement. We used ANOVA to test whether there is a significant difference in learning outcomes among the three experimental groups. To determine which groups have significantly different means, we performed the Tukey post hoc test. Analysis of the data collected aims to measure the impact of chatbot integration on learner satisfaction, engagement, self-regulation, learning outcomes, usefulness and usability. The results contribute to the understanding of chatbots as support tools in e-learning environments, and indicate that the integration of chatbots within e-learning platforms aims to improve the learning experience and foster learner success.

Estimation of carbon stocks in the areas of a seasonally dry tropical forest in the Brazilian semi-arid region

In addition to its ecological importance, the Caatinga biome, one of the most extensive seasonally dry tropical forests (SDTF) in the world, has a relevant socioeconomic role as it is used as a primary natural resource by local communities. However, inadequate ecosystem management practices have resulted in gradual loss of natural vegetation in this ecosystem. Carbon stock estimation is a parameter that can contribute as a support tool for managing and maintaining the few remaining natural vegetated areas. In this study, we calibrated and validated the CENTURY model to simulate carbon stocks in areas of the Caatinga, in the state of Pernambuco, and compared the predictive capacity of the CENTURY model with available estimates. In the validation dataset, the average for biomass stocks was 33.1 Mg C ha−1, this value is close to those observed in the literature for the region. The model also performed well when estimating carbon stocks in the soil (r2 = 0.79, p = 0.017). Ecosystem modeling combined with Geographic Information Systems (GIS) is a promising tool for estimating carbon stocks in the Caatinga, where field sampling campaigns are generally expensive and have scarce research funding opportunities. Furthermore, it also allows the evaluation of the effect of environmental changes on C stocks in long-term studies, which is essential for creating and implementing public policies to mitigate and adapt to the impacts of climate change on the ecosystem. However, additional efforts are needed to improve C estimates, especially in areas with a strongly negative water balance.

A Semantic Segmentation Method for Winter Wheat in North China Based on Improved HRNet

Winter wheat is one of the major crops for global food security. Accurate statistics of its planting area play a crucial role in agricultural policy formulation and resource management. However, the existing semantic segmentation methods for remote sensing images are subjected to limitations in dealing with noise, ambiguity, and intra-class heterogeneity, posing a negative impact on the segmentation performance of the spatial distribution and area of winter wheat fields in practical applications. In response to the above challenges, we proposed an improved HRNet-based semantic segmentation model in this paper. First, this model incorporates a semantic domain module (SDM), which improves the model’s precision of pixel-level semantic parsing and reduces the interference from noise through multi-confidence scale class representation. Second, a nested attention module (NAM) is embedded, which enhances the model’s capability of recognizing correct correlations in pixel classes. The experimental results show that the proposed model achieved a mean intersection over union (mIoU) of 80.51%, a precision of 88.64%, a recall of 89.14%, an overall accuracy (OA) of 90.12%, and an F1-score of 88.89% on the testing set. Compared to traditional methods, our model demonstrated better segmentation performance in winter wheat semantic segmentation tasks. The achievements of this study not only provide an effective tool and technical support for accurately measuring the area of winter wheat fields, but also have important practical value and profound strategic significance for optimizing agricultural resource allocation and achieving precision agriculture.

Effect of Management Information System on Growth of Agro-Firms in Anambra State

The study examined the effect of management information systems on the growth of agro-firms in Anambra State. The objectives were to: determine the effect of decision-making information systems on the Return on Investment (ROI) of agro-businesses in Anambra State, Nigeria, and ascertain the extent to which database management systems affect the ROI of agro-businesses in Anambra State, Nigeria. The study adopted a survey research design, with data generated from both primary and secondary sources. The data collection method was a questionnaire, which was randomly administered to staff of selected agro-firms. The population of the study was 6,727, while the sample size was 1,293, out of which 929 questionnaires were retrieved. The hypotheses were tested using the multiple regression analysis method at a 0.05% level of significance. The findings revealed that decision-making information systems had a significant effect on the ROI of agro-businesses in Anambra State, with a t-statistic of 7.743 and a probability value of 0.000. Additionally, database information systems had a significant effect on the ROI of agro-businesses in Anambra State, with a t-statistic of 2.476 and a probability value of 0.013. The study concluded that management information systems have a significant positive effect on agro-firms in Anambra State. It recommended that agricultural firms should invest in advanced decision support tools to aid data-driven decisions that maximize ROI. Furthermore, agro-business managers should focus on optimizing their database information systems to improve data organization and accessibility. Regular maintenance and updates of the database systems are crucial for ensuring accurate and timely information, which can positively impact ROI.

Maintaining Accuracy While Reducing Effort in Online Decision Making: A New Quantitative Approach for Multi-Attribute Decision Problems Based on Principal Component Analysis

This paper explores consumer decision making, particularly focusing on the increasing prevalence of choices on the Internet such as online shopping. Examining the fundamental question of how individuals decide how to decide, our paper draws upon the effort–accuracy framework. This framework indicates that people typically consider both the cognitive effort associated with employing a specific decision strategy and the decision quality (i.e., accuracy) implied by using a particular strategy. However, decision strategies with high accuracy imply high effort. Empirical evidence shows that people often use decision strategies that require little effort. As a result, accuracy is often not high. Against this backdrop, this paper introduces a quantitative approach leveraging principal component analysis (PCA) as a decision support tool. Based on a simulation study, the approach demonstrates that it is possible to maintain high accuracy with significantly reduced effort in multi-attribute decision situations where attribute information is available in a quantitative format. This demonstration is based on the example of two decision strategies, which are both theoretically and practically highly relevant: the multi-attribute utility model (MAU) and the elimination-by-aspects strategy (EBA). By employing PCA for dimensionality reduction, the approach becomes particularly advantageous for online shops and online comparison portals, presenting users with concise yet accurate information. It is important to emphasize that our PCA approach is designed for data with a natural ordering, primarily focusing on quantitative variables. Consequently, decision situations where qualitative variables (e.g., product design or color) play a role in the decision-making process will need further exploration in future studies. However, we present a first solution to this problem so that our approach, based on this solution, can be implemented by online shops and online comparison portals in the near future.

A IMPORTÂNCIA DA INTELIGÊNCIA EMPRESARIAL NO PROCESSO DE TOMADA DE DECISÃO DA EMPRESA X DE PINHALZINHO-SC

Over the years, companies are going through various organizational change processes, many transformations are taking place, and one of them is the insertion of technologies in the most diverse business segments. Information technology and business intelligence, Busines Intligence (BI), is becoming loyal and a great ally when it comes to strategy and decision making. Organizations are using such technologies as a support tool in the way they administer and manage their processes and businesses. These tools assist in the analysis of data and results that companies have, providing safer and more assertive decision making, in addition to offering greater security to owners. This study seeks to analyze the importance of this theme in the organizational environment of company X, located in the municipality of Pinhalzinho-SC. The data for this article were collected through an interview with the owners of the organization. In addition to doing an analysis on the subject, one of the objectives of this work is to present an improvement proposal for the company.

The development of a tool for GPs to manage overweight and obesity in children: A Delphi study

Background General practitioners (GPs) could play an important role in the management of overweight and obesity in children. However, GPs experience different barriers and are in need of supportive tools. In order to support GPs to identify, address and refer these children, new tools should be developed. Objective To establish consensus among GPs about the content topics of a supportive tool to identify, address and refer children with overweight and obesity in general practice. Methods A two-round Delphi study was conducted with GPs identified as experts. A concept of a supportive tool was constructed based on focus-group interviews with GPs, practice nurses and parents of children with and without overweight and literature. The tool was categorised into five topics: identifying, initiating and continuing weight-related conversations, referring and evaluating a tool manual. GPs evaluated statements on the tool’s topics in terms of importance. All statements were rated on a 5-point Likert scale and consensus was set at ≥70% of respondents agreeing with the statements. Results GPs agreed that a supportive tool must contain a child’s specialised BMI calculator; examples to initiate and to continue weight-related conversations with parents and children; a map with available interventions; and a manual including information and resources about health risks of overweight and obesity during childhood. Conclusion The content topics of a supportive tool for GPs to identify, discuss and refer children with overweight and obesity were determined through a consensus-driven process. Further validation and assessment are required through a feasibility and implementation study.

BUSINESS INTELLIGENCE E ERP (ENTERPRISE RESOURCE PLANNING) E SUAS VANTAGENS NAS ORGANIZAÇÕES.

Organizational change has been constantly discussed in organizational analyzes, with regard to the form and reasons why companies change or fail to change. It is necessary to understand that organizational change does not happen instantly, it is a gradual process, which takes place gradually. Currently, there are several support tools for organizations, so that these changes occur in a planned and more secure way. Business Intelligence (BI) is a very important aid for project management in the organization, as it collects and gathers company data, as well as parameters and performance indicators, transforming them into qualitative information. With Business Intelligence (BI) implemented correctly, the data that is and / or travels through the organization is available as consistent information to support decision making. ERP Systems (Enterprise Resource Planning), are able to contribute to the automation of activities and optimization of processes. Thus, organizations gain much more in productivity, cost reduction and optimized tasks, in addition to more efficient management, directly influencing decision making. With its premise of integrating data within the company, ERP Systems, generate faster access to higher quality information, emerges as a tool of great competitive advantage for Organizations in the market. Both of the tools mentioned above bring benefits to organizations.

The role of artificial intelligence in higher medical education and the ethical challenges of its implementation

Artificial intelligence (AI) is penetrating higher medical education; however, its adoption remains low. A PRISMA-S search of the Web of Science database from 2020 to 2024, utilizing the search terms “artificial intelligence,” “medicine,” “education,” and “ethics,” reveals this trend. Four key areas of AI application in medical education are examined for their potential benefits: Educational support (such as personalized distance education), radiology (diagnostics), virtual reality (VR) (visualization and simulations), and generative text engines (GenText), such as ChatGPT (from the production of notes to syllabus design). However, significant ethical risks accompany AI adoption, and specific concerns are linked to each of these four areas. While AI is recognized as an important support tool in medical education, its slow integration hampers learning and diminishes student motivation, as evidenced by the challenges in implementing VR. In radiology, data-intensive training is hindered by poor connectivity, particularly affecting learners in developing countries. Ethical risks, such as bias in datasets (whether intentional or unintentional), need to be highlighted within educational programs. Students must be informed of the possible motivation behind the introduction of social and political bias in datasets, as well as the profit motive. Finally, the ethical risks accompanying the use of GenText are discussed, ranging from student reliance on instant text generation for assignments, which can hinder the development of critical thinking skills, to the potential danger of relying on AI-generated learning and treatment plans without sufficient human moderation.

Understanding Test Convention Consistency as a Dimension of Test Quality

Unit tests must be readable to help developers understand and evolve production code. Most existing test quality metrics assess test code's ability to detect bugs. Few metrics focus on test code's readability. One standard approach to improve readability is the consistent application of conventions. We investigated test convention consistency as a dimension of test quality. We formalized test suite consistency as the extent to which alternatives are used within a code base and introduce two complementary metrics to capture this extent. We elaborated a catalog of over 30 test conventions for the Java language organized in 10 convention classes that group mutual alternatives. We developed tool support to detect occurrences of conventions, compute consistency metrics over a test suite, and view occurrences of conventions in the corresponding code. We applied our tools to study the consistency of the test suites of 20 large open-source Java projects. The study validates the design of the test convention classes, provides descriptive statistics on the range of consistency values for ten different convention classes, and enables us to link observed changes in consistency values to specific events in the change history of our target systems, thus providing evidence of the construct validity of the metrics. We conclude that analyzing test suite consistency via static analysis shows promise as a practical approach to help improve test suite quality.

Adoption, acceptance, and use of a decision support tool to promote timely investigations for cancer in primary care.

The complexities of diagnosing cancer in general practice has driven the development of quality improvement (QI) interventions, including clinical decision support (CDS) and auditing tools. Future Health Today (FHT) is a novel QI tool, consisting of CDS at the point-of-care, practice population-level auditing, recall, and the monitoring of QI activities. Explore the acceptability and usability of the FHT cancer module, which flags patients with abnormal test results that may be indicative of undiagnosed cancer. Interviews were conducted with general practitioners (GPs) and general practice nurses (GPNs), from practices participating in a randomized trial evaluating the appropriate follow-up of patients. Clinical Performance Feedback Intervention Theory (CP-FIT) was used to analyse and interpret the data. The majority of practices reported not using the auditing and QI components of the tool, only the CDS which was delivered at the point-of-care. The tool was used primarily by GPs; GPNs did not perceive the clinical recommendations to be within their role. For the CDS, facilitators for use included a good workflow fit, ease of use, low time cost, importance, and perceived knowledge gain. Barriers for use of the CDS included accuracy, competing priorities, and the patient population. The CDS aligned with the clinical workflow of GPs, was considered non-disruptive to the consultation and easy to implement into usual care. By applying the CP-FIT theory, we were able to demonstrate the key drivers for GPs using the tool, and what limited the use by GPNs.

Caregiver Values and Preferences Related to Surgical Decision-Making for Children with Medical Complexity

To uncover the values and preferences of the caregivers for children with medical complexity using the test case of surgical treatment decision-making for pediatric neuromuscular scoliosis that will inform the future development of a decision support tool in this population. We conducted a qualitative study of semistructured interviews of English- and Spanish-speaking caregivers of children with neuromuscular scoliosis from 2 geographically distinct children's hospitals. We used purposive sampling of language and treatment options selected to capture diverse experiences. Analysis was on the basis of grounded theory with synthesized caregiver values and preferences themes. From 47 participants, we completed 41 interviews (9 in Spanish). Caregivers had a mean age of 43.2years, were mostly White (66%), and had children with a mean age of 15.6. In total, 64% chose surgery. The following values and preferences were important to many caregivers: reducing scoliosis-related pain, minimizing mobility limitations to optimize socioemotional quality of life, limiting the impact of comorbidities on overall quality of life, information provided by peer support, the uncertainty of outcomes due to underlying comorbidities, and the uncertainty related to the anticipated progression of their child's scoliosis curve. Caregivers experienced immense uncertainty related to treatment outcomes due to their child's comorbidities. Caregivers of children with medical complexity may benefit from decision support that includes both values clarification exercises to help caregivers identify what of the many possible values and preferences are important to them and novel methods to communicate uncertainty in the care of CMC.

Reliability and validation of an electronic penicillin allergy risk-assessment tool in a pregnant population

BackgroundPenicillin allergy adversely impacts patient care, yet most cases do not have true allergies. Clinicians require efficient, reliable clinical tools to identify low risk patients who can be safely de-labeled. Our center implemented the FIRSTLINE electronic point-of-care decision support tool to help non-allergist practitioners risk stratify patients with penicillin allergy. We sought to explore the reliability and validity of this tool in relation to allergist assessment and actual patient outcomes. We additionally compared it with two other published stratification tools, JAMA and PENFAST, to assess ability to accurately identify low risk patients appropriate for direct oral challenge.MethodsIn this single-center, retrospective, observational study, 181 pregnant females with self-reported penicillin allergy between July 2019 to June 2021 at BC Women’s Hospital, Vancouver, Canada were used to assess the reliability and validity of all three tools. Physician-guided history of penicillin use and symptoms were used for scoring. Results and recommendations were compared to actual patient outcomes after clinician decision for direct oral challenge or intradermal tests. We compared the performance of JAMA, PENFAST and FIRSTLINE.Results181 patients were assessed. 176/181 (97.2%) patients were deemed not allergic. Each risk stratification tool labelled majority of patients as low risk with 88.4% of patients PENFAST 0–2, 60.2% of patients JAMA low risk, 86.7% of patients FIRSTLINE very low risk.ConclusionWe demonstrate that our point-of-care electronic algorithm is reliable in identifying low risk pregnant patients, as compared to an allergist assessment. To our knowledge, this is the first study to provide direct comparison between multiple decision support tools using the same population, minimizing participant bias. Providing clinical algorithms to risk stratify patients, can enable healthcare professionals to safely identify individuals who may be candidates for direct penicillin oral challenges versus needing referral to specialists. This increases the generalizability and efficiency of penicillin allergy de-labeling.

Design and development of a machine-learning-driven opioid overdose risk prediction tool integrated in electronic health records in primary care settings

BackgroundIntegrating advanced machine-learning (ML) algorithms into clinical practice is challenging and requires interdisciplinary collaboration to develop transparent, interpretable, and ethically sound clinical decision support (CDS) tools. We aimed to design a ML-driven CDS tool to predict opioid overdose risk and gather feedback for its integration into the University of Florida Health (UFHealth) electronic health record (EHR) system.MethodsWe used user-centered design methods to integrate the ML algorithm into the EHR system. The backend and UI design sub-teams collaborated closely, both informed by user feedback sessions. We conducted seven user feedback sessions with five UF Health primary care physicians (PCPs) to explore aspects of CDS tools, including workflow, risk display, and risk mitigation strategies. After customizing the tool based on PCPs’ feedback, we held two rounds of one-on-one usability testing sessions with 8 additional PCPs to gather feedback on prototype alerts. These sessions informed iterative UI design and backend processes, including alert frequency and reappearance circumstances.ResultsThe backend process development identified needs and requirements from our team, information technology, UFHealth, and PCPs. Thirteen PCPs (male = 62%, White = 85%) participated across 7 user feedback sessions and 8 usability testing sessions. During the user feedback sessions, PCPs (n = 5) identified flaws such as the term “high risk” of overdose potentially leading to unintended consequences (e.g., immediate addiction services referrals), offered suggestions, and expressed trust in the tool. In the first usability testing session, PCPs (n = 4) emphasized the need for natural risk presentation (e.g., 1 in 200) and suggested displaying the alert multiple times yearly for at-risk patients. Another 4 PCPs in the second usability testing session valued the UFHealth-specific alert for managing new or unfamiliar patients, expressed concerns about PCPs’ workload when prescribing to high-risk patients, and recommended incorporating the details page into training sessions to enhance usability.ConclusionsThe final backend process for our CDS alert aligns with PCP needs and UFHealth standards. Integrating feedback from PCPs in the early development phase of our ML-driven CDS tool helped identify barriers and facilitators in the CDS integration process. This collaborative approach yielded a refined prototype aimed at minimizing unintended consequences and enhancing usability.

Potential for an Electronic Clinical Decision Support Tool to Support Appropriate Antibiotic Use for Pediatric Diarrhea Among Village Doctors in Bangladesh.

Potential for an Electronic Clinical Decision Support Tool to Support Appropriate Antibiotic Use for Pediatric Diarrhea Among Village Doctors in Bangladesh.

A two-stage approach for modeling, performance evaluation, and decision support of disassembly processes

ABSTRACT This paper tackles an issue of disassembly lot-sizing within the framework of stochastic batch demand for multi-products featuring a two-level structure. The suggested methodology relies on a batch deterministic and stochastic Petri net as a modeling tool to address such problems in the context of stochastic processes. The primary objective is to determine the optimal sequencing of disassembly for each product type to meet stochastic batch demands of root items across multiple criteria. A novel mathematical model is introduced to minimize the cumulative costs associated with disassembly operations and extra costs, as well as holding costs for diverse products. In a subsequent stage, a decision support tool, namely the preference ranking organization method for enrichment evaluation method, is put forward for prioritizing different scenarios. For assessing the efficiency of the suggested approach, a real case study from the manufacturing industry is simulated. The simulation results prove the suggested approach’s capability to adapt to dynamic demands for leaf items throughout the planning horizon.

The Effects of Rubrics and Exemplars as Self-regulated Learning Tools on Students’ Development of Evaluative Judgement of Intercultural Competence: An Exploratory Study

This study aimed to explore the effects of a pedagogical intervention involving the combined application of rubrics and exemplars, as Self-Regulated Learning (SRL) support tools, on student’s development of the Evaluative Judgement (EJ) of Intercultural Competence (IC). A group of students from the General Required Courses department of a Saudi college participated in a quasi-experimental study involving the administration of an English writing module as part of an intensive English course. Coursework was designed based on Byram’s multidimensional IC model, guided by Liddicoat’s pathway model for IC development, framed within Panadero & Broadbent’s EJ framework, and mapped on Zimmerman’s Self-Reflection Phase (SRP) of the self-regulatory process. A mixed-method design was adopted to gain insights on the learning processes the students went through as well as their perceptions of and attitudes towards the learning experience. The results indicated a variety of SRP strategies at work and provided evidence for the positive effects of rubrics and exemplars on the enhancement of students’ EJ of IC. The results revealed several spheres where SRL, EJ, and IC relate and align to support students’ development and practice of sustainable skills that allow them to take control of their own learning and adapt in ever-changing environments.

Effects of poultry by-product meal and complete replacement of fish oil with alternative oils on growth performance and gut health of rainbow trout (Oncorhynchus mykiss): a FEEDNETICS™ validation study

BackgroundAquaculture, traditionally a form of biotechnology, has evolved to integrate innovative biotechnological applications, such as advanced feed formulations, aimed at improving the growth performance and health of farmed fish species. In the present study, the effects of feeding rainbow trout with novel feed formulations were investigated. Fish growth, gut and liver morphology, the concentration of fatty acids in the fillet, and volatile fatty acids in the gut were assessed. The study also validated scenarios from in vivo experiments using a nutrient-based model called FEEDNETICS™. This globally used model serves as a tool for data interpretation and decision support in the context of precision fish farming.MethodsAlternative protein and oil sources, including poultry by-product meal (PBM) and natural algae oil, were explored as sustainable replacements for fishmeal (FM) and fish oil (FO). A 90-day feeding trial was conducted using rainbow trout, comparing two isoproteic, isolipidic and isoenergetic diets. The control diet contained 15% FM, 5% PBM, and 8% FO, while the test diet replaced FM with 15% PBM and 5% feather meal hydrolysate (FMH), and fully substituted FO with VeraMaris® natural algae oil and rapeseed oil.ResultsPBM successfully replaced FM protein without negatively affecting feed intake, growth performance or feed utilization in trout. The combination of PBM and natural algae oil was well tolerated by the trout and showed no negative effects on gut health. A detailed analysis of fatty acids in the fillet revealed that PUFAs of the n3 and n6 series were significantly higher in the PBM group than in the FM group. Values of fatty acid-related health indexes, including atherogenicity index, and thrombogenicity index, confirmed the high nutritional value of trout filet, thus representing a healthy product for human. In addition, the predictions using the FEEDNETICS™ indicated that the tested novel alternative formulations are economically viable. The validation of the model for fish growth resulted in a Mean Absolute Percentage Error (MAPE) of 8%.ConclusionsThe FEEDNETICS™ application enhances our ability to optimize feeding strategies and improve production efficiency in the aquaculture industry. VeraMaris® algae oil and PBM could serve as viable and sustainable raw materials for fish feed, promoting environmentally friendly aquaculture practices.

Advancing titanium dioxide coated photocatalytic depolluting surfaces: Leveraging ASINA's roadmap for safer and sustainable solutions

This report, the second of its kind from ASINA project, aims at providing a roadmap with quantitative metrics for Safe(r) and (more) Sustainable by Design (SSbD) solutions for titanium dioxide (TiO2) nanomaterials (NMs). We begin with a brief description of ASINA’s methodology across the product lifecycle, highlighting the quantitative elements, such as the Key Performance Indicators (KPIs). We then propose a decision support tool for implementing SSbD objectives across various dimensions—functionality, cost, environment, and human health safety. This is followed by the main innovative findings, a consolidation of the technical processes involved, design rationales, experimental procedures, tools and models, used and developed, to deliver photocatalytic depolluting surfaces by spray- finishing techniques based on TiO2 NMs formulations. The roadmap is thoroughly described to inform similar projects through the integration of KPIs into SSbD methodologies, fostering data-driven decision-making. While specific results are beyond this report's scope, its primary aim is to demonstrate the roadmap (SSbD know-how) and promote SSbD-oriented innovation in nanotechnology. Finally, we provide a comparison of the approaches followed in two case studies that target different industrial sectors. This case-specific SSbD assessments provide a concrete exemplification of the addressed methodology that contributes to the efforts towards attaining a common roadmap for implementing SSbD solutions aligned with the EU’s Green Deal objectives.

Students’ perceptions of an artificially intelligent chatbot as a support tool to develop their research skills

PurposeThis research aims to evaluate students’ perception of using a chatbot to develop their understanding of the various parts of a research article, and their ability to apply what they have learned to write a new research plan.Design/methodology/approachThis research is qualitative in approach. The sample contained 10 students on a research skills course as part of the master of educational technologies program. The research instruments consisted of (1) semi-structured interviews to gather the students’ perceptions of the effectiveness of using a chatbot, and (2) observation notes to triangulate the interview results, relating to the students’ application of what they had learned from the teacher and ChatGPT, in new contexts.FindingsThis study found that the use of ChatGPT contributed to developing students’ knowledge of writing a research plan. The students were satisfied with their personalized learning experience, and believed that ChatGPT had improved their autonomy, competence and relatedness. These three variables had played a role in developing their application skill. However, there were concerns about using ChatGPT in learning, like limiting the students’ creativity, human interaction and critical thinking skills. There were also concerns over accuracy, ethics and plagiarism.Originality/valueThe originality of this study lies in its examination of how ChatGPT can help satisfy students' need for autonomy (having more knowledge to communicate with the app and control their choices), competence (feeling more capable of using artificial intelligence [AI] and possessing the necessary knowledge and skills to succeed) and relatedness (being less disappointed when failing to obtain satisfactory responses from the AI application), while improving their skills in application. According to self-determination theory (SDT), these factors affect students’ skills in applying what they have learned to new tasks. Therefore, this study extends the examination of SDT and its effect to include application skill, using qualitative methods to study the relationships between variables in depth.