Reimagining Data Storytelling with Generative AI

Evelyn ANG 

Data Literacy Programme
Office of the President, NUS

eve.ang@nus.edu.sg

Ang, E. (2024). Reimagining data storytelling with generative AI [Lightning talk]. In Higher Education Conference in Singapore (HECS) 2024, 3 December, National University of Singapore. https://blog.nus.edu.sg/hecs/hecs2024-eang/

SUB-THEME

Opportunities from Generative AI 

KEYWORDS

Data storytelling, Generative AIs, adult learners, ChatGPT-4o, custom GPTs 

CATEGORY

Lightning Talk

EXTENDED ABSTRACT

Data storytelling is a new superpower for making complex data accessible and engaging (Loewen, 2024a). Schwabish (2014) as well as Green and Brock (2000) highlight how visual and narrative elements enhance comprehension and persuasion, essential for effective data communication. Dykes (2020) demonstrates through real-world examples how compelling data stories can lead to more informed business decisions. Loewen (2024b) describes data storytelling as the art behind the science—the art of making sense out of a deluge of data, shaping it into something that sticks. The integration of generative AIs in storytelling creates more engaging narratives, akin to how bards once used music to enliven stories. Despite myths about data storytelling being just simplistic visualisation, it can be said to be a misconception. Dykes explained that effective data storytelling uses coherent narratives supported by meaningful visualisations to engage audiences deeply. Moreover, Generative AIs democratise the ability to analyse vast datasets, allowing humans to focus on creativity and emotional intelligence (Dykes, 2024). By combining AI capabilities with human adaptability, data storytellers can make data insights more compelling and actionable. Li (2024) has done a detailed scan into data storytelling tools available, and most are prototypes for research purposes. McKinsey & Company (2024) published an article reporting a surge in AI adoption in at least one business function in early 2024. Generative AI adoption is moving beyond professional setting and is much more likely to be used in both work and personal settings. 

 

Generative AI is here to stay and beckons the question how we can purpose generative AIs in data storytelling. 

 

In this lightning talk, I will highlight broadly what is good data storytelling as suggested by Knaflic (2015) in her book Storytelling with Data in areas (1) understanding the context, (2) choose appropriate visual display, (3) eliminate clutter, (4) focus attention where you want it, (5) think like a designer, and lastly (6) tell a story. Now to address the elephant in the roomhow will Gen AI fit into this picture? Recent work by Li (2024) proposed four distinct levels of AI involvement in working with data from the data workers’ perspectives, based on the levels of human agency versus AI automation. However, today’s advancement of AI has yet to be able to only perform a singular role with simple prompt inputs effectively. Kesari (2024) proposed a matrix of how different tools with GenAI are suited for different kinds of decisions to be made. 

 

How do we put all these together towards better data storytelling? I will broadly show how we can position fit-for-purpose use of GenAIs into the data storytelling preparatory work based on customGPTs. I will also weave in how GenAIs can be purposefully deployed so leaving us humans to do what we do best—creativity and connecting with our audience (Dyke, 2024). We will also visit how the most popular generative AIChatGPTwill be able to become your new companion in data storytelling through my CustomGPTNarratEve. I will also touch on using Custom GPTs (Loewen, 2024) that can make your data storytelling and preparation even more effective. 

REFERENCES

Dykes, B. (2020). Effective data storytelling: How to drive change with data, narrative, and visuals. John Wiley and Sons, Inc. 

Dykes, B. (2024). The Future of Data Storytelling is Augmented, not Automated. Forbes. https://www.forbes.com/sites/brentdykes/2024/02/27/the-future-of-data-storytelling-is-augmented-not-automated

Green, M. C., & Brock, T. C. (2000). The role of transportation in the persuasiveness of public narratives. Journal of Personality and Social Psychology, 79(5), 701-721. https://doi.org/10.1037//0022-3514.79.5.701

Kesari, G. (2024, 17 January). The Enduring Power of Data Storytelling in the Generative AI Era. MIT.edu. https://sloanreview.mit.edu/article/the-enduring-power-of-data-storytelling-in-the-generative-ai-era/

Knaflic, C. N. (2015).  Storytelling with Data: a data visualization guide for business professionals. Wiley. 

Li, H. (2024). Why is AI not a Panacea for Data Workers? An Interview Study on Human- AI Collaboration in Data Storytelling. arXiv 

Li, H. (2024). Where are we so far? Understanding Data Storytelling Tools from the perspective of Human-AI collaboration. arXiv 

Loewen, J. (2024). Custom GPT Creation For Data Visualization: A Step-by-Step Guide. Towardsai.net. https://towardsai.net/p/data-analysis/custom-gpt-creation-for-data-visualization-a-step-by-step-guide

Loewen, J. (2024a). Why Data Storytelling is Your New Superpower. Medium https://medium.com/data-storytelling-corner/why-data-storytelling-is-your-new-superpower-9f76e62762ce 

Loewen, J. (2024b). What the Heck is Data Storytelling Anyways? Here Are The Basics. Medium. https://medium.com/data-storytelling-corner/what-the-heck-is-data-storytelling-anyways-here-are-the-basics-c47c72cba44b

McKinsey & Company (2024). The state of AI in early 2024: Gen AI adoption spikes and starts to generate value. McKinsey https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai 

Schwabish, J. A. (2014). An economist’s guide to visualizing data. Journal of Economic Perspectives, 28(1), 209-234. https://dx.DOI.org/10.1257/jep.28.1.209

Leveraging Adult Learners’ Professional Experience Through Scenario-based Student-generated Questions And Answers In Engineering Mechanics

DU Hongjian1 and Stephen En Rong TAY2 

1Department of Civil and Environmental Engineering, College of Design and Engineering (CDE), NUS
2Department of the Built Environment, CDE, NUS

ceedhj@nus.edu.sgstephen.tay@nus.edu.sg 

Du, H., & Tay, S. E. R. (2024). Leveraging adult learners’ professional experience through scenario-based student-generated questions and answers in engineering mechanics [Paper presentation]. In Higher Education Conference in Singapore (HECS) 2024, 3 December, National University of Singapore. https://blog.nus.edu.sg/hecs/hecs2024-hdu-sertay/

SUB-THEME

Opportunities from Engaging Communities 

KEYWORDS

Engineering education, adult learners, relevance, student-generated questions and answers, assessment

CATEGORY

Paper Presentation

 

INTRODUCTION 

Adult learning is crucial for workforce development, ensuring that professionals can adapt to changes and thrive in their careers. Therefore, the Singapore government has implemented various initiatives including lifelong learning through the SkillsFuture Movement to address this challenge. The National University of Singapore (NUS) contributes to these efforts through the Bachelor of Technology (BTech) Programmes designed for polytechnic graduates working in the industry.  

 

Specifically, TCE2155 “Structural Mechanics and Materials”, a core course for BTech (Civil Engineering) received feedback from a control cohort expressing the need for evaluations of real-life structures to better understand course content. This observation agrees with the literature that adult learners are often more motivated by practical and relevant content that directly apply to their personal and professional lives (Merriam & Bierema, 2014). Hence, the use of scenario-based student-generated questions and answers (sb-SGQA) was adopted as the approach allows students to provide scenarios based on their professional experience. In brief, the sb-SGQA approach provides learners the opportunity to develop questions and answers to specific learning objectives within the course (Tay & Tay, 2021). This aligns with the adult learner experience, which is one of the six principles for adult education proposed by Knowles (1992). Hence, there is potential for sb-SGQA to allow the adult learner community to utilise their professional experience for learning. In addition, past experience with implementing sb-SGQA provided confidence and familiarity with the approach (Du & Tay, 2022).  

 

Hence, this paper aims to answer two key questions:  

  1. a) Does sb-SGQA help adult learners link their professional experiences with course content? 
  2. b) How can sb-SGQA impact adult learners’ performance?

 

METHODOLOGY 

TCE2155 is offered for first year BTech (Civil Engineering) undergraduates, who must be at least aged 21 and have two years of full-time work experience. The sb-SGQA approach was introduced in TCE2155, with student feedback compared across three runs: the initial run without sb-SGQA (control in AY2020/21) and two subsequent runs with sb-SGQA (intervention in AY2022/23 and AY2023/24). Data collected included student assignments, final exam grade, feedback, and module scores. Detailed methodology of the sb-SGQA implementation follows a previous work by the authors (Du and Tay, 2022). In the initial run without sb-SGQA, a conventional teaching approach was employed. Students were given a pre-defined structural analysis question, and they were required to calculate the force and stress in the structure. This approach focused on the application of formulae and calculations, without involving real-life scenarios or encouraging students to generate their own questions and solutions.

 

RESULTS AND DISCUSSION 

The number of enrolled students in TCE215 and those that responded to the survey are:  

AY2020/21 (control cohort): 33 enrolled and 17 responded 

AY2022/23 (intervention cohort): 28 enrolled and 16 responded 

AY2023/24 (intervention cohort): 29 enrolled and 8 responded  

 

As displayed in Figure 1, the feedback score for the course and teacher improved in the intervention runs. One limitation lies in the limited sample size of less than 40 for the cohorts, which may need additional control and intervention cohorts in subsequent academic years to further validate the promising results. For example, the dip in score for “Course” and “Thinking ability” could be attributed to academic abilities of the intervention cohorts. Nevertheless, it is interesting that despite the plausible difference in academic abilities of the intervention cohorts, the score for “Teacher” and “Interest” remains high. Students gave higher ratings to the module and the lecturer. Reports also revealed higher ratings in areas such as “The teacher has enhanced my thinking ability” and “The teacher has increased my interest in the subject.” Qualitative feedback included comments such as “This module is very interesting and can relate to my working life” and “Able to apply it to daily work” indicating the practical benefits of sb-SGQA. 

Figure 1. Teaching score from students regarding the course, teacher, increased interest in the subject, and thinking ability in control (AY2020/21) and intervention (AY2022/23 and AY2023/24) cohorts. 

 

Figure 2 shows the final exam grade distributions of TCE2155 in the three runs. Note that no students in the intervention cohort scored 0-15 and no students in the control cohort scored 90-100. This demonstrates that sb-SGQA can encourage all adult learners, especially the weaker students, to perform better in the final exam. Furthermore, an analysis of the submitted assignments in the intervention cohort highlighted how many students were able to use their professional experience to design the questions and answers (refer to Figure 3). In the control cohort, adult learners would not be able to draw upon their professional experience to contextualise the learning objectives in the course.  

Figure 2. Final exam grade distributions of the final exam in control (AY2020/21) and intervention (AY2022/23 and AY2023/24) cohorts.  

 

Figure 3. Sample of submitted assignment from AY2023/24 (intervention cohort). 

 

CONCLUSION 

The sb-SGQA approach was implemented in TCE2155 within the BTech (Civil Engineering) programme. As a result, adult learners were able to link their professional experience with the course content, which was shown to impact adult learners’ performance in the assignments submitted. With no additional hardware or software required, the sb-SGQA presents itself as a cost-effective method for improving engineering education for adult learners. 

 

REFERENCES

Chin, C. C., & Brown, D. E., (2013). Student-generated questions: A meaningful aspect of learning in science, International Journal of Science Education, 24(5), 521-549. http://dx.DOI.org/10.1080/09500690110095249   

Du, H. J., & Tay, S. E. R. (2022). Using scenario-based student-generated questions to improve the learning of engineering mechanics: A case study in civil engineering [Paper presentation]. In Higher Education Campus Conference (HECC) 2022, 7-8 December, National University of Singapore. https://ctlt.nus.edu.sg/wp-content/uploads/2024/10/ebooklet-i.pdf  

Merriam, S. B., & Bierema, L. L., (2013). Adult Learning: Linking Theory and Practice [eBook]. Jossey-Bass. 

Knowles, M. S. (1992). Applying principles of adult learning in conference presentations. Adult Learning, 4(1), 11-14. https://doi.org/10.1177/104515959200400105

Tay, M. X. Y., & Tay, S. E. R. (2021). Scenario-Based Student-generated Questions for Students to Develop and Attempt for Authentic Assessments [Workshop]. In International Society for the Scholarship of Teaching and Learning, 27th October 2021. 

Viewing Message: 1 of 1.
Warning

Blog.nus accounts will move to SSO login soon. Once implemented, only current NUS staff and students will be able to log in to Blog.nus. Public blogs remain readable to non-logged in users. (More information.)