Conversational Agent Self-Disclosure via Sentiment Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conversational agents (CAs) face challenges in gaining user trust due to their inability to engage in genuine self-disclosure, leading to distrust and premature termination of interactions, as they often mimic self-disclosure without actual basis, which was previously a subjective human process.
Innovation Solution
A computing system configured to analyze user input using natural language understanding (NLU) and sentiment analysis to determine when to include self-disclosure in responses, providing information about the CA's identity, memories, and problem-solving processes to enhance user trust and interaction quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If CAs mimic self-disclosure without actual basis, then user trust may be initially gained, but user trust deteriorates and interactions terminate prematurely
Solution Approach 1:
The CA performs sentiment analysis on user inputs and automatically determines appropriate self-disclosure responses based on detected emotions, enabling the system to serve itself in building trust without human intervention. The CA analyzes its own operational state and user feedback to generate authentic self-disclosure about its capabilities and limitations.
Solution Approach 2:
The system implements a feedback loop where user responses to self-disclosure are analyzed to adjust future disclosure strategies. Sentiment analysis of user feedback informs the CA about what types of self-disclosure are effective, creating a continuous improvement cycle that enhances trust while maintaining appropriate interaction duration.
2Reliability
If CAs perform genuine self-disclosure analysis using sentiment analysis, then user acceptance increases, but system complexity increases
Solution Approach 1:
The patent replaces complex human psychological judgment mechanisms with automated sentiment analysis algorithms. Instead of requiring human operators to analyze user emotions and determine appropriate self-disclosure, the system uses natural language processing and sentiment analysis to automatically detect user emotional states and generate appropriate responses, reducing operational complexity while maintaining effectiveness.
3Reliability
If CAs include information about their self in responses, then user trust increases, but information processing requirements increase
Solution Approach 1:
The system extracts only the essential elements needed for self-disclosure from the CA's operational data, such as sentiment analysis results and key capability information. Rather than processing and disclosing all available information about the CA's internal state, the system selectively extracts and presents only the most relevant self-information that builds user trust while minimizing processing overhead.
Data Source
AI summary
Conversational agents (CAs) may analyze language input and generate and output a response to a user. For example, when receiving a user's support request, the CA may determine whether to conduct self-disclosure by including information about the CA's “self” in a response to the user. For example, based on performing sentiment analysis of a support request user input, the CA may determine that the user is expressing negative emotions. Based on the user's expression of negative emotions, the CA may perform self-disclosure as part of generating a response to the user. A CA that is configured to engage in self-disclosure, for instance by including information about a CA's self in an output response, may increase users' acceptance of the CA, which may make a user more likely to trust and/or interact with a CA.