Neural nets for sustainability conversations: modeling discussion disciplines and their impacts
Abstract We live in the age polarization, where conversations on matters of sustainability more often produce acrimony or stalemate than productive action. Better understanding conversation features and their impacts may lead to better innovation, solution-design, and ongoing collabor...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer London
2023
|
| Online Access: | https://hdl.handle.net/1721.1/152194 |
| _version_ | 1811081228739149824 |
|---|---|
| author | Pugh, Katrina Musavi, Mohamad Johnson, Teresa Burke, Christopher Yoeli, Erez Currie, Emily Pugh, Benjamin |
| author2 | Sloan School of Management |
| author_facet | Sloan School of Management Pugh, Katrina Musavi, Mohamad Johnson, Teresa Burke, Christopher Yoeli, Erez Currie, Emily Pugh, Benjamin |
| author_sort | Pugh, Katrina |
| collection | MIT |
| description | Abstract
We live in the age polarization, where conversations on matters of sustainability more often produce acrimony or stalemate than productive action. Better understanding conversation features and their impacts may lead to better innovation, solution-design, and ongoing collaboration. We describe a study to test alternate machine learning models for classifying six “discussion disciplines”, which are conversation features associated with rhetorical intent. The model providing the best outcome used the Bi-directional Encoder Representations from Transformers (BERT) layered with a Residual Network (ResNet). The training data were 1135 utterances from Maine aquaculture town hall-like meetings and similar conversations, which had been hand-coded for the discussion disciplines. In addition, we generated 300 phrases corresponding to three conversation outcomes: Intent-to-Act, Options-Generation, and Relationship-Building. We then used the trained model and information retrieval to classify a large corpus of 591 open-source transcripts, containing over 21,000 utterances. A binary logistic regression analysis showed that two discussion disciplines, “Inclusion” and “Courtesy,” had positive, statistically significant, impacts on Intent-to-act: a 10 percentage point increase in the share of the Inclusion or Courtesy yielded a 45% or 34% increase, respectively, in the likelihood of Intent-to-Act. This study shows the applicability of neural networks in modeling conversations and identifying the dialog acts that can provide measurable and predictable impact on conversation outcomes. Conversational intelligence can support a variety of human interactions, such as town halls, policy-deliberations, private–public partnerships, and sustainability teamwork. |
| first_indexed | 2024-09-23T11:43:29Z |
| format | Article |
| id | mit-1721.1/152194 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:43:29Z |
| publishDate | 2023 |
| publisher | Springer London |
| record_format | dspace |
| spelling | mit-1721.1/1521942024-01-10T18:28:07Z Neural nets for sustainability conversations: modeling discussion disciplines and their impacts Pugh, Katrina Musavi, Mohamad Johnson, Teresa Burke, Christopher Yoeli, Erez Currie, Emily Pugh, Benjamin Sloan School of Management Abstract We live in the age polarization, where conversations on matters of sustainability more often produce acrimony or stalemate than productive action. Better understanding conversation features and their impacts may lead to better innovation, solution-design, and ongoing collaboration. We describe a study to test alternate machine learning models for classifying six “discussion disciplines”, which are conversation features associated with rhetorical intent. The model providing the best outcome used the Bi-directional Encoder Representations from Transformers (BERT) layered with a Residual Network (ResNet). The training data were 1135 utterances from Maine aquaculture town hall-like meetings and similar conversations, which had been hand-coded for the discussion disciplines. In addition, we generated 300 phrases corresponding to three conversation outcomes: Intent-to-Act, Options-Generation, and Relationship-Building. We then used the trained model and information retrieval to classify a large corpus of 591 open-source transcripts, containing over 21,000 utterances. A binary logistic regression analysis showed that two discussion disciplines, “Inclusion” and “Courtesy,” had positive, statistically significant, impacts on Intent-to-act: a 10 percentage point increase in the share of the Inclusion or Courtesy yielded a 45% or 34% increase, respectively, in the likelihood of Intent-to-Act. This study shows the applicability of neural networks in modeling conversations and identifying the dialog acts that can provide measurable and predictable impact on conversation outcomes. Conversational intelligence can support a variety of human interactions, such as town halls, policy-deliberations, private–public partnerships, and sustainability teamwork. 2023-09-21T19:46:15Z 2023-09-21T19:46:15Z 2023-09-01 2023-09-17T03:09:59Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/152194 Pugh, Katrina, Musavi, Mohamad, Johnson, Teresa, Burke, Christopher, Yoeli, Erez et al. 2023. "Neural nets for sustainability conversations: modeling discussion disciplines and their impacts." PUBLISHER_CC en https://doi.org/10.1007/s00521-023-08819-z Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer London Springer London |
| spellingShingle | Pugh, Katrina Musavi, Mohamad Johnson, Teresa Burke, Christopher Yoeli, Erez Currie, Emily Pugh, Benjamin Neural nets for sustainability conversations: modeling discussion disciplines and their impacts |
| title | Neural nets for sustainability conversations: modeling discussion disciplines and their impacts |
| title_full | Neural nets for sustainability conversations: modeling discussion disciplines and their impacts |
| title_fullStr | Neural nets for sustainability conversations: modeling discussion disciplines and their impacts |
| title_full_unstemmed | Neural nets for sustainability conversations: modeling discussion disciplines and their impacts |
| title_short | Neural nets for sustainability conversations: modeling discussion disciplines and their impacts |
| title_sort | neural nets for sustainability conversations modeling discussion disciplines and their impacts |
| url | https://hdl.handle.net/1721.1/152194 |
| work_keys_str_mv | AT pughkatrina neuralnetsforsustainabilityconversationsmodelingdiscussiondisciplinesandtheirimpacts AT musavimohamad neuralnetsforsustainabilityconversationsmodelingdiscussiondisciplinesandtheirimpacts AT johnsonteresa neuralnetsforsustainabilityconversationsmodelingdiscussiondisciplinesandtheirimpacts AT burkechristopher neuralnetsforsustainabilityconversationsmodelingdiscussiondisciplinesandtheirimpacts AT yoelierez neuralnetsforsustainabilityconversationsmodelingdiscussiondisciplinesandtheirimpacts AT currieemily neuralnetsforsustainabilityconversationsmodelingdiscussiondisciplinesandtheirimpacts AT pughbenjamin neuralnetsforsustainabilityconversationsmodelingdiscussiondisciplinesandtheirimpacts |