Generating follow-up questions on the fly could significantly improve conversational survey quality and user experiences by enabling a more dynamic and personalized survey structure. In this paper, we proposed a novel task for knowledge-driven follow-up question generation in conversational surveys. We constructed a new human-annotated dataset of human-written follow-up questions with dialogue history and labeled knowledge in the context of conversational surveys. Along with the dataset, we designed and validated a set of reference-free Gricean-inspired evaluation metrics to systematically evaluate the quality of generated follow-up questions. We then propose a two-staged knowledge-driven model for the task, which generates informative and coherent follow-up questions by using knowledge to steer the generation process. The experiments demonstrate that compared to GPT-based baseline models, our two-staged model generates more informative, coherent, and clear follow-up questions.

Espressive, a pioneer in artificial intelligence (AI) for enterprise service management (ESM) and a 2019 Gartner Cool Vendor, announced the latest advances in its virtual support agent (VSA) Espressive Barista, including Barista Conversational Surveys, the first AI-based survey to inform decision making while triggering actions in real time. Additionally, the new Barista Smart Ticketing capability employs machine learning (ML) to build a predictive model to accurately classify, assign, and prioritize tickets, enabling fast deployment and improved mean time to resolve (MTTR). "In today's economic climate, it has become extremely important for enterprises to implement digital technologies enabling them to innovate, execute, and pivot faster than the competition," said Pat Calhoun, CEO and founder of Espressive. "The challenge CIOs face is that any new technology has to deliver an extremely fast time to value with a positive impact on workforce productivity. Today's announcements further position Espressive customers to meet both of those objectives."

The rise of increasingly more powerful chatbots offers a new way to collect information through conversational surveys, where a chatbot asks open-ended questions, interprets a user's free-text responses, and probes answers when needed. To investigate the effectiveness and limitations of such a chatbot in conducting surveys, we conducted a field study involving about 600 participants. In this study, half of the participants took a typical online survey on Qualtrics and the other half interacted with an AI-powered chatbot to complete a conversational survey. Our detailed analysis of over 5200 free-text responses revealed that the chatbot drove a significantly higher level of participant engagement and elicited significantly better quality responses in terms of relevance, depth, and readability. Based on our results, we discuss design implications for creating AI-powered chatbots to conduct effective surveys and beyond.

Net Promoter Score (NPS) is used to measure the loyalty of a company's customer relationships. It is used by many companies to both measure customers experience and predict business growth. NPS provides the core measurement for CX management programs round the world and is primarily built around one simple question. How likely is it that you would recommend our company to a friend or colleague? Simply take away the percentage of detractors from the percentage of promoters to get your Net Promoter Score.

Are brands interacting with their customers in the right way to get useful feedback? The answer is: no, not always. Given that a recent Forbes interview with a survey expert indicates that response rates are down to an all-time low of less than 2%, brands could be forgiven for thinking their customers don't want to talk to them. However, the rise in the number of people using social media to contact brands would suggest otherwise. It is simply that they have survey fatigue, and the flaws in many survey programs are putting customers off from the start.