There is an ever-growing array of artificial intelligence-based tools available for research use by students and faculty. These tools often use AI to create and find connections and themes between academic papers pulled from very large databases. The tools then use the power of visualizations to illustrate the connections and the power of summary to concisely describe the information, much the same way as abstracts summarize the contents of academic journal articles. Other tools allow deep analysis of documents (which could be articles) or datasets.
Some of the most well-known tools include the following:
Tools for searching for information —
*emphasizes connections and themes among academic papers
*”Elicit tends to work best for empirical domains that involve experiments and concrete results. This type of research is common in biomedicine and machine learning. Elicit does not currently answer questions or surface information that is not written about in an academic paper. It tends to work less well for identifying facts (e.g. “How many cars were sold in Malaysia last year?”) and in theoretical or non-empirical domains.”
*searches Semantic Scholar
*can upload your own papers to Elicit for analysis
*has free, paid, and organization options
*example — What will be the impact of AI on academic libraries?
The integration of AI in academic libraries has the potential to significantly transform library management, resource utilization, and research experience (C 2024). However, this transformation is not without its challenges, including ethical and privacy concerns, staff training, and user-centered approaches (C 2024). AI is expected to impact search and resource discovery, scholarly publishing, and learning in academic libraries, with potential roles for libraries in data acquisition and curation, AI tool acquisition, and infrastructure building (Cox 2019). The application of AI in academic libraries is expected to enhance services and engage users, particularly through virtual reference services and conversational agents (Choukimath 2019). The adoption of AI in academic libraries is likely to influence the work of librarians, with potential approaches to AI applications and factors influencing their adoption (Cox 2022).
Elicit June 16, 2024
*”Litmaps uses the citation network to discover literature that’s easily overlooked with other search methods. This, combined with our ever-evolving algorithms and automated alert system, means never missing a relevant paper again.”
*uses open access metadata ingested from CrossRef, Semantic Scholar, and OpenAlex (which, in turn, take data from many sources including DOAJ, Pubmed, and Pubmed Central).
*visualizes connections between papers
*has free, paid, and organization options
*searches MEDLINE and Semantic Scholar
*emphasizes and visualizes connections between papers
*requires an account but is free to use.
*connection to Zotero
*”helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence.”
*ingests text and metadata from both open and for-profit sources
*can upload your own papers to Scite for analysis
*after a free trial, there are individual and corporate/institutional subscription options
*connection to Zotero and Mendeley
*a combination of many academic tools–AI search tool, bibliographic management software, writing aid, AI detector, and more
*free, premium, and institutional subscription options
*can upload your own documents for AI analysis
Tools for document/data analysis —
*”Our platform is not just another document search tool. Leveraging the robust capabilities of advanced AI technologies, docAnalyzer acts as a conversational interface for your PDFs, allowing you to ask context-specific questions and receive pinpointed answers in real-time. Say goodbye to the tedious task of manually sifting through pages upon pages of academic papers. Whether you’re seeking a particular statistic from a study, verifying a hypothesis, or comparing theories across multiple documents, our tool offers a seamless, interactive experience.”
*free, basic, and pro plans with options to buy additional credits
*works by uploading your own documents into the tool, running an AI analysis of the documents, and then searching them (searching the database you created) to gain insights
*their market is much broader than academic research, also aimed at business
*focused on datasets; requires an account to use
*”AI SaaS service centered around personal and enterprise datasets. Designed to unlock the full potential of your data, Powerdrill enables you to use natural language to effortlessly interact with your datasets for tasks ranging from simple Q&As to insightful BI analysis.”
Follow the story at Artificial Intelligence and Education.
Questions? Please let me know (engelk@grinnell.edu).
