English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Using chatbots to deliver recommendations is increasingly popular. The designof recommendation chatbots has primarily been taking an information-centricapproach by focusing on the recommended content per se. Limited attention is onhow social connection and relational strategies, such as self-disclosure from achatbot, may influence users' perception and acceptance of the recommendation.In this work, we designed, implemented, and evaluated a social chatbot capableof performing three different levels of self-disclosure: factual information(low), cognitive opinions (medium), and emotions (high). In the evaluation, werecruited 372 participants to converse with the chatbot on two topics: moviesand COVID-19 experiences. In each topic, the chatbot performed small talks andmade recommendations relevant to the topic. Participants were randomly assignedto four experimental conditions where the chatbot used factual, cognitive,emotional, and adaptive strategies to perform self-disclosures. By training atext classifier to identify users' level of self-disclosure in real-time, theadaptive chatbot can dynamically match its self-disclosure to the level ofdisclosure exhibited by the users. Our results show that users reciprocate withhigher-level self-disclosure when a recommendation chatbot consistentlydisplays emotions throughout the conversation. Chatbot's emotional disclosurealso led to increased interactional enjoyment and more positive interpersonalperception towards the bot, fostering a stronger human-chatbot relationship andthus leading to increased recommendation effectiveness, including a highertendency to accept the recommendation. We discuss the understandings obtainedand implications to future design.

Dialoging Resonance: How Users Perceive, Reciprocate and React to Chatbot's Self-Disclosure in Conversational Recommendations