In Search of New Product Ideas: Identifying Ideas in Online Communities by Machine Learning and Text Mining

Abstract

Online communities are attractive sources of ideas relevant for new product development and innovation. However, making sense of the 'big data' in these communities is a complex analytical task. A systematic way of dealing with these data is needed to exploit their potential for boosting companies' innovation performance. We propose a method for analysing online community data with a special focus on identifying ideas. We employ a research design where two human raters classified 3,000 texts extracted from an online community, according to whether the text contained an idea. Among the 3,000, 137 idea texts and 2,666 non-idea texts were identified. The human raters could not agree on the remaining 197 texts. These texts were omitted from the analysis. The remaining 2,803 texts were processed by using text mining techniques and used to train a classification model. We describe how to tune the model and which text mining steps to perform. We conclude that machine learning and text mining can be useful for detecting ideas in online communities. The method can help researchers and firms identify ideas hidden in large amounts of texts. Also, it is interesting in its own right that machine learning can be used to detect ideas.

How good are ideas identified by an automatic idea detection system?

“…Using text analytics and machine learning methods, Christensen, Nørskov, et al (2017) develop such an algorithm and demonstrate its classification performance and efficiency for the case of extracting new product ideas from an online community related to Lego. show that the same principles can be applied to extract ideas for innovations from a community related to craft brewing.…”

“…We believe that the method introduced by Christensen, Nørskov, et al (2017) shows potential for aiding firms in their search for innovative ideas and may thus serve as a tool for extending the boundaries of inbound open innovation. Still, some questions must be addressed before such a method can be implemented in a firm's innovation processes.…”

“…Artificial intelligence systems that leverage big data allow more and more tasks to be solved in an automatic manner. Whilst in the past these were predominantly tasks of a mundane and repetitive nature, advances in text analytics and machine learning have also made it possible to solve more complex problems (Christensen, Nørskov, Frederiksen, & Scholderer, 2017).…”

“…Artificial intelligence systems that leverage big data allow more and more tasks to be solved in an automatic manner. Whilst in the past these were predominantly tasks of a mundane and repetitive nature, advances in text analytics and machine learning have also made it possible to solve more complex problems (Christensen, Nørskov, Frederiksen, & Scholderer, 2017).A problem that continues to occupy scholars and practitioners of new product development is how to obtain and select ideas for new products (e.g., di Gangi, Wasko, & Hooker, 2010;Frederiksen & Knudsen, 2017;van den Ende, Frederiksen, & Prencipe, 2015). In the context of inbound open innovation, Ooms, Bell, and Kok (2015), for example, argue that firms can enhance their receptivity-i.e., their capacity to absorb more diverse external knowledge from more varied sources-by engaging with social media.…”

“…The aim of the present paper is to fill these two gaps. Specifically, we would like to contribute in two respects to the literature:• Our first contribution is to assess whether ideas from an online community, identified by an artificial intelligence system such as the one described by Christensen, Nørskov, et al (2017), will also be perceived as ideas by company-internal staff.• Our second contribution is to investigate whether the ideas that are detected by the system will also be perceived as good ideas by company-internal staff.There is a reason why we believe these issues are important. We address potential acceptance problems that were also in the general innovation literature initially seen as barriers for the uptake of usercontributed ideas by companies.…”