Advancing Conversational AI with Shona Slang: A Dataset and Hybrid Model for Digital Inclusion

The proliferation of artificial intelligence (AI) systems, from virtual assistants [Kepuska and Bohouta, 2018] to recommendation engines [Gomez-Uribe and Hunt, 2015] and autonomous vehicles [Shladover, 2018], has reshaped human-machine interaction. Y et, African languages, with over 2,000 spoken across the continent [Eberhard et al., 2023], remain severely underrepresented in NLP due to their low-resource status [Ahia and Boakye, 2023, Nekoto et al., 2020]. This exclusion risks exacerbating the digital divide, limiting access to AI-driven services in critical domains like education, healthcare, and governance [Ndichu et al., 2024, Joshi et al., 2020]. Shona, a Bantu language spoken by millions in Zimbabwe and southern Zambia, exemplifies this challenge. Existing Shona corpora primarily consist of formal texts, such as news articles or religious documents [Eberhard et al., 2023], while everyday communication, particularly among younger speakers, is dominated by slang, code-mixing with English, and informal expressions [Eisenstein, 2013]. Standard NLP models, trained on formal data, struggle to process these dynamic linguistic patterns, hindering the development of culturally relevant conversational AI.