User innovation communities, where end users voluntarily share their ideas about new products or services, have become an important source of innovation. While efforts have been made to extract and develop ideas from these sources, existing studies have largely focused on company‐led efforts to facilitate user participation, rather than on voluntary user discussions within communities themselves. As a remedy, this research proposes to directly target those voluntary ideas from user innovation communities for product/service innovation. Because quantities of textual information within these communities are rather massive, we propose a modified and integrated approach of text‐mining (TM) and case‐based reasoning (CBR). Specifically, by constructing two casebases on ideas and existing products using TM and checking for overlap between the two using CBR, the approach enables the identification of opportunities for innovation and reference products for adaptation. We demonstrate the approach through a case of mobile apps in Apple App Store, and our findings suggest that the approach can help firms and users/developers broaden the source of ideas and leverage them into new product concepts.