Opinionated chatbots are increasingly present on online platforms and have the potential to shape public discourse by influencing individuals' viewpoints before they engage in discussions. Despite their growing presence, the impact of interacting with opinionated chatbots on subsequent online interactions remains largely unexplored. This study investigated how exposure to different types of opinionated chatbots, specifically those expressing opposing, reinforcing, or balanced viewpoints, affected participants' subsequent online discussions. In a controlled experiment with 83 participants, we found that interacting with an opinionated chatbot that consistently opposed participants' arguments led to greater shifts in opinion, indicating enhanced openness to revising one's initial stance. Conversely, participants who interacted with a chatbot that consistently reinforced their views were more likely to adopt more agreeable communication styles in subsequent conversations with others. Furthermore, interactions with different types of opinionated chatbots resulted in varying levels of trust, as well as different perceptions of chatbots and human interlocutors. Our findings indicate that opinionated chatbots can influence both individuals' opinions on social topics and their communication behaviors in online environments. This presents a trade-off for future designers seeking to facilitate cognitive flexibility in changing opinions while maintaining positive user experiences and trust in the chatbots during public discourse. We discuss the implications for designing opinionated chatbots to promote more constructive and less polarized online discussions.

Non-native speakers (NNSs) frequently encounter speaking difficulties in multilingual communication, where existing approaches have shown promise in facilitating NNSs' comprehension and participation in real-time communication. However, they often overlook providing direct speaking support, where anxiety stemming from linguistic inadequacy and uncertain communication dynamics are core issues. To address this, we introduce an AI tool with translation for real-time speaking support. It also builds a channel for mutual understanding with native speakers (NSs) to mitigate interactional anxiety. Through a within-subjects experiment involving 25 NNS-NS pairs (N = 50) on collaborative tasks, our findings suggest that the tool improved NNSs' speaking self-efficacy, reduced their interactional anxiety, and decreased their workload, particularly for NNSs with below-average language proficiency. Furthermore, NNSs reported a significant sense of support from their NS partners via the mutual understanding channel, and NSs also clearly perceived the NNSs' need for assistance and displayed a strong sense of communicative responsibility. This research underscores the potential of AI support in real-time NNS communication and the importance of promoting mutual understanding, culminating in actionable design insights for future work.

Recruitment interviews are cognitively demanding interactions in which interviewers must simultaneously listen, evaluate candidates, take notes, and formulate follow-up questions. To better understand these challenges, we conducted a formative study with eight HR professionals, from which we derived key design goals for real-time AI support. Guided by these insights, we developed InterPilot, a prototype system that augments interviews through intelligent note-taking and post-interview summary, adaptive question generation, and real-time skill–evidence mapping. We evaluated the system with another seven HR professionals in mock interviews using a within-subjects design. Results show that InterPilot reduced documentation burden without increasing overall workload, but introduced usability trade-offs related to visual attention and interaction complexity. Qualitative findings further reveal tensions around trust and verification when AI suggests highly specific technical questions. We discuss implications for designing future real-time human–AI collaboration in professional settings, highlighting the need to balance assistance granularity, attentional demands, and human agency.