Structured Argumentation System for Asynchronous Forecasting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online message boards lack structure and guidance, leading to unproductive discussions due to off-topic drift, lack of source validation, and biases such as anchoring and confirmation bias, making it difficult for users to reach consensus on forecasts.
Innovation Solution
A system that presents users with structured prompts for numerical and explanatory responses, displays ordered lists of other users' responses to mitigate biases, and uses distance measures to rank disagreements, allowing for consensus or mediated forecasts, with automated evaluation of citations and rationales to promote productive debate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users provide unstructured responses on message boards, then the system is simple to operate, but the discussion becomes unstructured and difficult to analyze
Solution Approach 1:
The response is segmented into distinct components: a numerical forecast portion and an explanatory rationale portion. This segmentation maintains ease of operation while introducing structure, allowing users to provide forecasts in their natural way while the system captures and organizes the data into analyzable components.
Solution Approach 2:
The system introduces an intermediary processing layer that receives unstructured user responses and transforms them into structured data formats. The processing circuit acts as a mediator between the simple user interface and the structured analysis requirements, maintaining ease of operation while enabling structured discussion analysis.
2Ease of operation
If users are allowed to post responses freely without guidance, then the system is easy to use, but discussions drift off-topic and lack focus
Solution Approach 1:
The system performs preliminary action by presenting users with structured prompts that guide them to provide focused responses. The prompt is prepared in advance with specific guidance on what information is needed (numerical forecast and rationale), ensuring discussions remain on-topic while users still participate easily.
Solution Approach 2:
The system provides feedback to users by displaying ordered lists of other responses and highlighting relevant information. This feedback mechanism keeps users engaged with the discussion focus while maintaining ease of participation, preventing drift by continuously showing what others are saying in relation to the original question.
3Extent of automation
If users rely on their own biases and initial opinions, then the system requires minimal intervention, but consensus is difficult to reach
Solution Approach 1:
The system introduces an intermediary processing layer that objectively evaluates and ranks responses based on criteria such as rationale quality and citation support. This mediator prevents users from being solely influenced by their own biases while maintaining automation, creating a reliable consensus process that transcends individual subjective opinions.
Solution Approach 2:
The system replaces the mechanical process of manual consensus-building with automated evaluation mechanisms. The processing circuit automatically assesses responses, ranks them by distance from the original question, and determines consensus or mediates forecasts, eliminating the need for users to manually navigate biased opinions while maintaining reliability.
4Device complexity
If the system displays all responses without ordering, then the system is simple to implement, but users cannot efficiently identify relevant information
Solution Approach 1:
The system replaces simple unordered display with automated computational ranking based on distance measures. The processing circuit calculates the distance between each response and the original question, then orders responses accordingly. This substitution maintains implementation simplicity while dramatically improving the ability to detect and measure relevant information.
Solution Approach 2:
The system changes the parameter of response organization from unordered to ordered based on distance from the original question. By transforming the display parameter from simple listing to distance-based ranking, the system maintains implementation simplicity while making relevant information easily identifiable through the ordered presentation.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for collecting and processing user input. In some embodiments the method includes presenting a first user with a prompt for eliciting a first response, the first response including a numerical portion including one or more numbers, and an explanatory portion; receiving, from the first user, the first response; receiving from each of a plurality of other users, a respective response of a plurality of other responses; and displaying, to the first user, an ordered list of other responses. Within the ordered list, a second response, of the plurality of other responses, may be earlier than a third response, of the plurality of other responses, the second response being, according to a measure of distance, more distant, than the third response, from the first response.