DIA: Supporting Teacher Professional Development in Low Infrastructure Settings

 Governments in developing countries aim to improve education through novel teaching approaches as taught in pedagogical programs. These pedagogical programs rely on government teacher training infrastructure and face challenges in rural parts of Africa where there is a lack of experts and teachers are isolated. Thus, pedagogical programs consider using technology to overcome some of these challenges. 

Prior work has used a conversational agent to address the challenges of limited expert knowledge and providing personalized interactions. Recent work used virtual communities on social media for teachers to support each other through online interactions. Still, it is unclear how these two promising research areas can translate to rural African contexts with low technology infrastructure. Additionally, teachers in these contexts are newly adopting technology and thus require additional support to accommodate technology adoption. Therefore, there is a need to discover appropriate conversational agent designs that support teacher communities in low-infrastructure settings. 

This design process must overcome several practical, technological, and theoretical challenges to find appropriate designs in this context. Beyond being usable, the design has to support an intervention aligned with the pedagogical program. Lastly, theoretical grounding for designing technology in low-resource contexts is still emerging. 

Therefore, I use an iterative design-based research (DBR) approach by working closely with teachers in rural Côte d’Ivoire to develop a technology that helps them to implement a pedagogical program. My work iteratively identifies design directions and validates these directions through prototypes shared among the teacher community. Through a progression of three studies (Study 1, Study 2 and Study 3), I studied the impact of these design directions at scale. 

My work led to a conversational agent called "DIA." that I designed by working with Ivorian teachers. Key findings in these studies were that teachers supported each other in the community and valued community-based features in a conversational agent. Therefore, this led to my thesis question: How does a conversational agent that supports a virtual community of practice (vCOP) impact teachers in low iii infrastructure settings?. To answer this question, I conducted a large-scale, year?long study to understand the impact of community-based features at scale (Study 4). 

Study 4 involved a longitudinal quasi-experiment with 400 teachers in two different regions of rural Côte d’Ivoire to investigate the impact of two variations of a conver?sational agent. In one region, a conversational agent with individual support was deployed, and in another region, a conversational agent with community support was deployed. The objective was to assess motivation, knowledge, and technology adoption changes over the school year. The findings indicated that community support positively affected motivation, enhancing agency within the community. Teacher knowledge showed some improvement, with a slight but statistically significant overall increase. Although the community condition increased technology usage, the results did not reach statistical significance. The results favor utilizing community support in conversational agents for teachers in low-infrastructure settings. 

This dissertation extends the literature on Human-Centered AI in low-infrastructure settings through iterative design-based research. On the theoretical front, my work expands literature on virtual communities of practice to an Ivorian context. My work has created opportunities to design for teachers "aspirations" or long-term desires. My work has also provided design recommendations for governments to utilize a conversational agent to support teachers implementing pedagogical programs.