Skip to Main Content
Xavier Library Home Employee Hub Student Hub

Artificial Intelligence

This guide is a basic overview of Artificial Intellegence through the lens of student research in an academic library.

AI Integrations in Databases

Across the board, academic database providers are weaving AI into their services in 2025, but each in a way that aligns with their platform’s purpose:

  • Content aggregators like EBSCO and ProQuest use AI to simplify search and help users digest articles (summaries, concept explanations).
  • Digital libraries like JSTOR use AI to enhance reading comprehension and exploration without replacing the scholarly material.
  • Major publishers like Elsevier deploy powerful generative AI to let researchers query vast collections and speed up literature reviews (with rigorous source attribution to maintain trust).
  • Educational platforms like Gale focus on AI that aids discovery and analytical skills (topic finding, text analysis), keeping the researcher in the loop.

In all cases, the goal is to save researchers time and effort while preserving accuracy and scholarly integrity. Users should always remain critical thinkers – the AI tools provide assistance, not absolute answers – but when used wisely, these features can significantly enhance the research experience, from quickly screening hundreds of papers to engaging interactively with a single book chapter. Each database’s approach to AI offers unique strengths, and together they point toward a future where scholarly research is more efficient and richly supported by “intelligent” tools.

AI integration in academic databases falls into a few key categories:

  • AI-Assisted Search: Natural language query handling, semantic search improvements, and AI-driven query expansion.
  • Automatic Summarization: On-demand summaries or key point extractions from articles to help researchers quickly gauge relevance.
  • Conversational AI/Chatbots: Interactive tools that allow users to ask questions about a document or topic and get answers with references.
  • Recommendation & Analysis Tools: Features that suggest related content, compare findings across papers, or perform text analysis (topic modeling, etc.).
Database/Platform AI Feature(s) Details/Examples
EBSCOhost & EBSCO Discovery

AI Insights (Summaries)
Natural Language Search
  • AI Insights generates 2–5 key “insights” (bullet-point statements) from a full-text article, letting researchers quickly judge its relevance. These summaries are grounded in the article text (using Retrieval-Augmented Generation) and are reviewed by librarians to ensure accuracy.
  • Natural Language Search (NLS) lets users search in plain English questions or statements; the system uses AI to expand queries and interpret intent, improving result relevance and context understanding. (Both features introduced in 2025 across EBSCO databases and the EDS discovery platform.)
ProQuest (Clarivate)

Research Assistant
(Summaries, Concepts & Topics)

 The ProQuest Research Assistant is an AI-powered helper embedded in ProQuest Central and other Clarivate academic platforms. Within any full-text document, it provides a “Key Takeaway” summary of the text, explains important terms or concepts in that document (with definitions and why they’re important), and offers “next step” suggestions. It can also recommend new research topics related to the document, giving users pre-formulated search queries to explore with one click. These features act as a guided research aid rather than just a chatbot – helping students understand content and discover more, while upholding academic integrity (no un-sourced answers). Clarivate has rolled out similar assistants in Web of Science, Ebook Central, and other products.
JSTOR

Interactive AI Tool
(Chat & Summaries)

 JSTOR’s Interactive Research Tool (beta) uses AI to let users engage in a conversation with JSTOR content. When viewing a journal article, book chapter, etc., users can do several AI-driven actions: get a summary of the item’s main points, ask questions in natural language about that specific text (the tool’s answers are based only on that source’s content), and find related content (it suggests similar articles/chapters). Essentially, it’s like having a specialized research chatbot that “has read” the article and can answer your questions or point you to further readings. This helps especially with dense scholarly texts – students can clarify concepts or significance via a quick Q&A. Users need to create a free JSTOR account to access and use the tool. (The tool was piloted in 2023 and expanded to more institutions in 2024, and is expected to reach all JSTOR users in 2025.)
ScienceDirect (Elsevier)

ScienceDirect AI
(Generative Q\&A, Reading Assistant, Comparison)

 

ScienceDirect AI is Elsevier’s new generative AI integration (launched March 2025) that serves as a research companion on the ScienceDirect platform. Key features include: Ask ScienceDirect – a cross-document search that uses generative AI to answer research questions by pulling from 14+ million full-text articles and book chapters, returning an instant summary with citations and even snippet excerpts from the sources.

  • Reading Assistant – a chat feature that lets you ask questions about a specific article or chapter you’re reading; the AI will answer based on that document’s content (with links to where in the text the answer comes from). It even suggests follow-up research questions to explore.
  • Compare Experiments – an innovative tool that takes multiple articles selected by the user and builds a comparative table of their key experimental details (goals, methods, results), helping researchers systematically see parallels and differences across studies. All outputs include references to ensure transparency.
Gale Platforms (Cengage)

Topic Finder (Visual NLP)
Digital Scholar Lab (Text Mining)

Gale’s products (e.g., Academic OneFile, General OneFile, etc.) include AI-driven tools focused more on exploration and analysis rather than generative answers.

  • Topic Finder is an interactive visual search tool that uses AI algorithms to cluster search results by topic and subtopic. For a given query, it produces a wheel or tile visualization of related terms and themes; clicking a segment shows articles on that subtopic. This helps users, especially students, brainstorm and refine topics by seeing connections that a traditional list of results might not show. Topic Finder is essentially an “AI-fueled brainstorming tool” based on term frequency and co-occurrence, not a generative model.
  • Digital Scholar Lab, a platform for scholars to apply text mining and NLP on Gale Primary Sources. Within the Lab, users can run tools like document clustering (topic modeling), sentiment analysis, and named-entity recognition across large text corpora – enabling AI-powered analysis for digital humanities research.

These Lab tools have been around since 2018–2019 and emphasize responsible, transparent use of AI/NLP on content.

Content was developed using responses generated with Copilot Researcher using two prompts: "use this list of databases https://libguides.xavier.edu/az.php to find which ones have added language to their sites and contracts about artificial intelligence" and "what AI features each of these databases now include?"

Before you jump into using GenAI for research, try these warm-up exercises to get a feel for the responses...and to see if you are smarter than a GPT!

  • Ask a series of questions about a topic you know a lot about (what are you an “expert” in) (does not need to be academic)
    • Are the answers accurate?
    • Does it provide links to resources about the topic?
    • What happens when you correct it?
  • Ask it to write a story about two fictional characters from different worlds (IPs) meeting in one of the character’s worlds. Then ask it to write the story set in the other character’s world. 
    • Was the depiction of the characters accurate?
    • Was the writing entertaining?
    • Would you want to read/watch more of the story it produced?

Generative AI Research Tools

  • Microsoft Copilot: Researcher + Analyst
    • Included in your Xavier Microsoft suite. Researcher acts like a research assistant, designed to support complex, multi-step projects. Analyst functions more like a data scientist, using chain-of-thought reasoning to explore and analyze data.  
  • ResearchRabbit
    • Search for papers and authors, monitor new literature, visualize research landscapes, and collaborate with colleagues.” -Mission statement
    • Free and search powered by PubMed and Semantic Scholar
  • Semantic Scholar
    • Free, AI-driven search and discovery tools, and open resources for the global research community.
  • Keenious
    • Analyzes inputs (text, URL, pdf) to find relevant scholarly articles and related topics
    • Free for core features with limited results and analysis, $10/month for expanded results and unlimited analysis.

Productivity AI Tools

  • Goblin Tools
    • A collection of small, simple, single-task tools, mostly designed to help neurodivergent people with tasks they find overwhelming or difficult.
    • Most tools will use AI technologies in the back-end to achieve their goals. Currently this includes OpenAI's models. As the tools and backend improve, the intent is to include ethical alternatives.
  • Perplexity
    • Perplexity AI is an innovative AI-powered search engine that combines the capabilities of large language models with real-time web searching to provide comprehensive, up-to-date answers to user queries. 
    • Perplexity is available as a web app, mobile app, and Chrome extension. Standard plan: free forever. Pro plan: $20 per month or $200 per year.

The Library does not endorse any specific AI technologies, and encourages users to be cautious about sharing personal information when using AI tools. 

4 P’s of Prompting
1. Priming–Give it context.
2. Purpose–Give it a task.
3. Persona-Give it a descriptive profile.
4. Prompt Tuning –Iterate, separate
For example:

You are a Google Cloud program manager (1). Draft an executive summary email to (2) [persona] based on [details about relevant program docs] (3). Limit to bullet points (4)

Prompting Tips

  • Use natural language.
    • Write as if you’re speaking to another person.
    • Express complete thoughts in full sentences.
  • Be specific and iterate.
    • Tell the program what you need it to do (summarize, write, change the tone, create).
    • Provide as much context as possible.
  • Be concise and avoid complexity.
    • State your request in brief —but specific —language. Avoid jargon.
    • Most successful prompts average 21 words, but most people post only 9-word prompts.
  • Make it a conversation.
    • Fine-tune your prompts if the results don’t meet your expectations or if you believe there’s room for improvement.
    • Use follow-up prompts and an iterative process of review and refinement to yield better results

Privacy Tips

  • Protect confidential data
    • Do not enter personal or confidential data into publicly-available Generative AI tools. Information shared with Generative AI tools using default settings is not private and could expose proprietary or sensitive information to unauthorized parties.
  • Review content before publication
    • AI-generated content can be inaccurate, misleading, or entirely fabricated (sometimes called “hallucinations”) or may contain copyrighted material. You are responsible for any content that you publish that includes AI-generated material.
  • Adhere to existing academic policy
    • Review Xavier’s student and faculty handbooks and policies. Xavier will be developing and updating their policies as we better understand the implications of using Generative AI tools. In the meantime, faculty should be clear with students they’re teaching and advising about their policies on permitted uses, if any, of Generative AI in classes and on academic work.Students are also encouraged to ask their instructors for clarification about these policies as needed.
  • Be alert for phishing
    • Generative AI has made it easier for malicious actors to create sophisticated phishing emails and “deepfakes” (i.e., video or audio intended to convincingly mimic a person’s voice or physical appearance without their consent) at a far greater scale.