Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Promoting Research Collaboration with Open Data Driven Team Recommendation in Response to Call for Proposals

Siva Likitha Valluru, Biplav Srivastava, Sai Teja Paladi, Siwen Yan, Sriraam Natarajan

TL;DR

The paper addresses forming interdisciplinary research teams to respond to funding calls by treating it as a group recommendation problem that leverages open data on RFPs and researcher profiles. It proposes four methods (M0–M3) to form candidate teams and a novel Goodness Score $g_i$ that combines redundancy, set size, coverage, and $k$-robustness to guide top-k recommendations. Quantitative results show that more informed methods yield higher-quality teams while reducing the number of options, with M3 achieving the best performance ($G$ around $0.53$) in a 434 RFP/200 researcher setting, alongside a large-scale human study confirming usefulness and relevance. The work demonstrates deployment feasibility (ULTRA) and generality by extending evaluation to IIT-Roorkee, India, and discusses future directions in data quality, explainability, and broader domain applicability.

Abstract

Building teams and promoting collaboration are two very common business activities. An example of these are seen in the TeamingForFunding problem, where research institutions and researchers are interested to identify collaborative opportunities when applying to funding agencies in response to latter's calls for proposals. We describe a novel system to recommend teams using a variety of AI methods, such that (1) each team achieves the highest possible skill coverage that is demanded by the opportunity, and (2) the workload of distributing the opportunities is balanced amongst the candidate members. We address these questions by extracting skills latent in open data of proposal calls (demand) and researcher profiles (supply), normalizing them using taxonomies, and creating efficient algorithms that match demand to supply. We create teams to maximize goodness along a novel metric balancing short- and long-term objectives. We validate the success of our algorithms (1) quantitatively, by evaluating the recommended teams using a goodness score and find that more informed methods lead to recommendations of smaller number of teams but higher goodness, and (2) qualitatively, by conducting a large-scale user study at a college-wide level, and demonstrate that users overall found the tool very useful and relevant. Lastly, we evaluate our system in two diverse settings in US and India (of researchers and proposal calls) to establish generality of our approach, and deploy it at a major US university for routine use.

Promoting Research Collaboration with Open Data Driven Team Recommendation in Response to Call for Proposals

TL;DR

The paper addresses forming interdisciplinary research teams to respond to funding calls by treating it as a group recommendation problem that leverages open data on RFPs and researcher profiles. It proposes four methods (M0–M3) to form candidate teams and a novel Goodness Score that combines redundancy, set size, coverage, and -robustness to guide top-k recommendations. Quantitative results show that more informed methods yield higher-quality teams while reducing the number of options, with M3 achieving the best performance ( around ) in a 434 RFP/200 researcher setting, alongside a large-scale human study confirming usefulness and relevance. The work demonstrates deployment feasibility (ULTRA) and generality by extending evaluation to IIT-Roorkee, India, and discusses future directions in data quality, explainability, and broader domain applicability.

Abstract

Building teams and promoting collaboration are two very common business activities. An example of these are seen in the TeamingForFunding problem, where research institutions and researchers are interested to identify collaborative opportunities when applying to funding agencies in response to latter's calls for proposals. We describe a novel system to recommend teams using a variety of AI methods, such that (1) each team achieves the highest possible skill coverage that is demanded by the opportunity, and (2) the workload of distributing the opportunities is balanced amongst the candidate members. We address these questions by extracting skills latent in open data of proposal calls (demand) and researcher profiles (supply), normalizing them using taxonomies, and creating efficient algorithms that match demand to supply. We create teams to maximize goodness along a novel metric balancing short- and long-term objectives. We validate the success of our algorithms (1) quantitatively, by evaluating the recommended teams using a goodness score and find that more informed methods lead to recommendations of smaller number of teams but higher goodness, and (2) qualitatively, by conducting a large-scale user study at a college-wide level, and demonstrate that users overall found the tool very useful and relevant. Lastly, we evaluate our system in two diverse settings in US and India (of researchers and proposal calls) to establish generality of our approach, and deploy it at a major US university for routine use.
Paper Structure (26 sections, 2 figures, 3 tables, 4 algorithms)

This paper contains 26 sections, 2 figures, 3 tables, 4 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Setting
  4. Problem Formulation
  5. Use Cases
  6. System Design
  7. Metrics
  8. Redundancy.
  9. Set Size.
  10. Coverage.
  11. k-Robustness.
  12. Goodness Score.
  13. Methods
  14. M0: Random Team Formation.
  15. M1: Team Formation Using String Matching.
  16. ...and 11 more sections

Figures (2)

  • Figure 1: A demo use case, ${UC}_1$, showing a team participant view of ULTRA.
  • Figure 2: Sankey breakdown of the 212 responses we received from our human study. It shows four categories of nodes: (1) use cases, (2) methods, (3) scale of relevancy, and (4) scale of usefulness. Each line maps a connection from node type to another, showing the flow of interaction that users had with ULTRA.