Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing
Macro-task crowdsourcing presents a promising approach to address wicked problems like climate change by leveraging the collective efforts of a diverse crowd. Such macro-task crowdsourcing requires facilitation. However, in the facilitation process, traditionally aggregating and synthesizing text co...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Netherlands
2024
|
| Online Access: | https://hdl.handle.net/1721.1/155946 |
| _version_ | 1811082157975666688 |
|---|---|
| author | Gimpel, Henner Laubacher, Robert Meindl, Oliver Wöhl, Moritz Dombetzki, Luca |
| author_facet | Gimpel, Henner Laubacher, Robert Meindl, Oliver Wöhl, Moritz Dombetzki, Luca |
| author_sort | Gimpel, Henner |
| collection | MIT |
| description | Macro-task crowdsourcing presents a promising approach to address wicked problems like climate change by leveraging the collective efforts of a diverse crowd. Such macro-task crowdsourcing requires facilitation. However, in the facilitation process, traditionally aggregating and synthesizing text contributions from the crowd is labor-intensive, demanding expertise and time from facilitators. Recent advancements in large language models (LLMs) have demonstrated human-level performance in natural language processing. This paper proposes an abstract design for an information system, developed through four iterations of a prototype, to support the synthesis process of contributions using LLM-based natural language processing. The prototype demonstrated promising results, enhancing efficiency and effectiveness in synthesis activities for macro-task crowdsourcing facilitation. By streamlining the synthesis process, the proposed system significantly reduces the effort to synthesize content, allowing for stronger integration of synthesized content into the discussions to reach consensus, ideally leading to more meaningful outcomes. |
| first_indexed | 2024-09-23T11:58:29Z |
| format | Article |
| id | mit-1721.1/155946 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:58:29Z |
| publishDate | 2024 |
| publisher | Springer Netherlands |
| record_format | dspace |
| spelling | mit-1721.1/1559462024-09-20T04:41:22Z Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing Gimpel, Henner Laubacher, Robert Meindl, Oliver Wöhl, Moritz Dombetzki, Luca Macro-task crowdsourcing presents a promising approach to address wicked problems like climate change by leveraging the collective efforts of a diverse crowd. Such macro-task crowdsourcing requires facilitation. However, in the facilitation process, traditionally aggregating and synthesizing text contributions from the crowd is labor-intensive, demanding expertise and time from facilitators. Recent advancements in large language models (LLMs) have demonstrated human-level performance in natural language processing. This paper proposes an abstract design for an information system, developed through four iterations of a prototype, to support the synthesis process of contributions using LLM-based natural language processing. The prototype demonstrated promising results, enhancing efficiency and effectiveness in synthesis activities for macro-task crowdsourcing facilitation. By streamlining the synthesis process, the proposed system significantly reduces the effort to synthesize content, allowing for stronger integration of synthesized content into the discussions to reach consensus, ideally leading to more meaningful outcomes. 2024-08-05T18:49:42Z 2024-08-05T18:49:42Z 2024-07-30 2024-08-04T03:14:08Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/155946 Gimpel, H., Laubacher, R., Meindl, O. et al. Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing. Group Decis Negot PUBLISHER_CC en 10.1007/s10726-024-09894-w Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer Netherlands Springer Netherlands |
| spellingShingle | Gimpel, Henner Laubacher, Robert Meindl, Oliver Wöhl, Moritz Dombetzki, Luca Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing |
| title | Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing |
| title_full | Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing |
| title_fullStr | Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing |
| title_full_unstemmed | Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing |
| title_short | Advancing Content Synthesis in Macro-Task Crowdsourcing Facilitation Leveraging Natural Language Processing |
| title_sort | advancing content synthesis in macro task crowdsourcing facilitation leveraging natural language processing |
| url | https://hdl.handle.net/1721.1/155946 |
| work_keys_str_mv | AT gimpelhenner advancingcontentsynthesisinmacrotaskcrowdsourcingfacilitationleveragingnaturallanguageprocessing AT laubacherrobert advancingcontentsynthesisinmacrotaskcrowdsourcingfacilitationleveragingnaturallanguageprocessing AT meindloliver advancingcontentsynthesisinmacrotaskcrowdsourcingfacilitationleveragingnaturallanguageprocessing AT wohlmoritz advancingcontentsynthesisinmacrotaskcrowdsourcingfacilitationleveragingnaturallanguageprocessing AT dombetzkiluca advancingcontentsynthesisinmacrotaskcrowdsourcingfacilitationleveragingnaturallanguageprocessing |