Conversational Swarm Intelligence amplifies the accuracy of networked groupwise deliberations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929203678543872 |
|---|---|
| author | Rosenberg, Louis Willcox, Gregg Schumann, Hans Mani, Ganesh |
| author_facet | Rosenberg, Louis Willcox, Gregg Schumann, Hans Mani, Ganesh |
| contents | Conversational Swarm Intelligence (CSI) is a communication technology that enables large, networked groups (25 to 2500 people) to hold real-time conversational deliberations online. Modeled on the dynamics of biological swarms, CSI enables the reasoning benefits of small-groups with the collective intelligence benefits of large-groups. In this pilot study, groups of 25 to 30 participants were asked to select players for a weekly Fantasy Football contest over an 11-week period. As a baseline, participants filled out a survey to record their player selections. As an experimental method, participants engaged in a real-time text-chat deliberation using a CSI platform called Thinkscape to collaboratively select sets of players. The results show that the real-time conversational group using CSI outperformed 66% of survey participants, demonstrating significant amplification of intelligence versus the median individual (p=0.020). The CSI method also significantly outperformed the most popular choices from the survey (the Wisdom of Crowd, p<0.001). These results suggest that CSI is an effective technology for amplifying the intelligence of groups engaged in real-time large-scale conversational deliberation and may offer a path to collective superintelligence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_04112 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Conversational Swarm Intelligence amplifies the accuracy of networked groupwise deliberations Rosenberg, Louis Willcox, Gregg Schumann, Hans Mani, Ganesh Human-Computer Interaction Conversational Swarm Intelligence (CSI) is a communication technology that enables large, networked groups (25 to 2500 people) to hold real-time conversational deliberations online. Modeled on the dynamics of biological swarms, CSI enables the reasoning benefits of small-groups with the collective intelligence benefits of large-groups. In this pilot study, groups of 25 to 30 participants were asked to select players for a weekly Fantasy Football contest over an 11-week period. As a baseline, participants filled out a survey to record their player selections. As an experimental method, participants engaged in a real-time text-chat deliberation using a CSI platform called Thinkscape to collaboratively select sets of players. The results show that the real-time conversational group using CSI outperformed 66% of survey participants, demonstrating significant amplification of intelligence versus the median individual (p=0.020). The CSI method also significantly outperformed the most popular choices from the survey (the Wisdom of Crowd, p<0.001). These results suggest that CSI is an effective technology for amplifying the intelligence of groups engaged in real-time large-scale conversational deliberation and may offer a path to collective superintelligence. |
| title | Conversational Swarm Intelligence amplifies the accuracy of networked groupwise deliberations |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2401.04112 |