The premise behind the project is deceptively simple: researchers already describe themselves, their publications and their proposals in enormous textual detail. Funding agencies likewise describe every grant call in careful prose. The problem is that traditional search tools treat these descriptions as bags of keywords rather than as meaningful text. A keyword search for a term like machine learning, for example, may return opportunities that mention the phrase in passing while missing deeply relevant calls that describe the same concepts in different words. The Research Highlighter-MatchMaker Project instead applies natural language processing, the branch of artificial intelligence that lets computers interpret the meaning and context of human language, to analyze the full text of research profiles, abstracts and proposals, and then compares that analysis against funding announcements. Because the matching happens at the level of meaning rather than literal word overlap, the system can surface opportunities that a conventional database search would never reveal.

Users interact with the platform through a front-end portal that offers three distinct search modes, each tailored to a different kind of question. The first, Search By Name, lets a researcher look up their own profile and receive funding recommendations matched to their publication history and stated interests. The second, Search By Topic, groups researchers who work in related areas, making it easier to discover colleagues across departments or even across institutions who share a common scientific concern. The third, Search By Text, is perhaps the most flexible: a user can paste in an arbitrary passage, such as a draft grant abstract or a research summary, and the system will return funding suggestions that align with the substance of that text. This means the tool can be used at the very moment it matters most, when a proposal is taking shape and the right sponsor has not yet been identified.

Under the hood, the platform draws on two major external data sources to keep its picture of the research landscape current. Publication records come from the Scopus API, one of the largest curated databases of peer-reviewed literature in the world, providing a rich and continuously updated account of who publishes what, with whom and where. Funding opportunity data comes from SPIN, a widely used database of grant programs maintained for academic institutions. By integrating both streams, the system can align a researcher’s demonstrated output with the sponsors most likely to fund their next project. Rather than relying on manual curation, which ages quickly and scales poorly, the platform refreshes its understanding as new papers appear and new calls are announced.

One of the platform’s most practical features is its automated email listserv, which pushes personalized funding recommendations directly to researchers on a regular schedule. This transforms the tool from a system a researcher must remember to consult into an active assistant that keeps working in the background. For faculty members juggling teaching, mentoring and administration, and for graduate students who may not yet know which agencies fund their subfield, this kind of passive, personalized awareness can make a substantial difference. The developers emphasize that the recommendations are generated from the researcher’s own profile and recent activity, so the alerts grow more relevant as the individual’s research evolves.

The technology arrives at a moment when competition for research funding has intensified across nearly every discipline. Application success rates at major federal agencies have fallen for years, and institutions are under growing pressure to demonstrate that they are helping their scholars win external support. At the same time, the most exciting scientific questions increasingly sit between fields, requiring teams that blend computational expertise with domain knowledge in biology, engineering, the social sciences or the humanities. Yet researchers often have no systematic way of discovering who else on their own campus, let alone at a partner institution, is working on a compatible problem. By clustering researchers by topic and suggesting potential collaborations, the Highlighter-MatchMaker platform aims to lower the barriers to exactly these interdisciplinary partnerships.

The developers point to a second population that stands to benefit disproportionately: early-career researchers and graduate students. Established professors accumulate visibility over decades, appearing in internal newsletters, institutional databases and the memories of their colleagues. Junior scientists, by contrast, may not yet be integrated into those informal networks, which means they frequently miss opportunities simply because nobody knows what they are working on. Because the platform builds its understanding of a researcher from publication records and free-text input, it can match a first-year graduate student’s interests to relevant funding just as readily as it matches a senior faculty member’s long record. The system is also designed to be inclusive of external collaborators, extending its reach beyond a single campus.

Architecturally, the platform is built to grow. The team describes the system as extensible, meaning that additional categories of research-related data, such as technology transfer agreements or compliance documents, could be incorporated in future versions. That flexibility matters because the administrative side of research touches many databases beyond publications and grants, and a matching engine that can reason over all of them could become a comprehensive hub for institutional research support. The technology is currently at technology readiness level three, indicating that the core concepts and functionality have been demonstrated at an early proof-of-concept stage, and the underlying intellectual property is patent pending. The Research Foundation for the State University of New York is offering the platform for licensing as part of its broader effort to translate SUNY innovations into economic and academic impact.

The scale of the system’s potential user base reflects the scale of SUNY itself. With 64 colleges and universities, four academic health centers and research expenditures of nearly one and a half billion dollars in fiscal year 2025, SUNY oversees close to a quarter of all academic research in New York State. Even a modest improvement in the efficiency with which its researchers find funding and collaborators would represent significant value. But the vision behind the Research Highlighter-MatchMaker Project extends beyond any single institution. As research data grows ever larger and collaboration ever more essential, the tools that help scientists find each other, and find the money to pursue shared questions, may become as fundamental to the scientific enterprise as the laboratory and the library. In that sense, an AI-driven matchmaker for the research world is less a convenience than a quiet piece of infrastructure for the future of discovery.

Subject of Research: A natural language processing platform that matches researchers with funding opportunities and potential collaborators using integrated publication and grant databases.

Article Title: Research highlighter-matchmaker project

Article References: Research highlighter-matchmaker project. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: artificial intelligence, natural language processing, research funding, grant matching, research collaboration, interdisciplinary research, University at Albany, SUNY, Scopus, SPIN database, early-career researchers, technology licensing