About Web of Science Research Assistant
The Web of Science Research Assistant is designed with and for researchers to help you get more out of the Web of Science Core Collection, the world’s most trusted multidisciplinary citation database.
The research assistant is a generative AI-powered tool that offers natural language, multilingual search capabilities, concise overviews of results, task-based guided walkthroughs, and visualizations to enhance your research. It delivers responses to research questions and contextual prompts to help you explore potential paths forward in your research. It supports a wide variety of research needs, including but not limited to:
- Exploring a topic
- Starting a literature review
- Finding a journal to publish in
- Identifying experts in a field
How are responses generated for Document Search and Question & Answer queries?
To help you better understand how the Research Assistant generates responses to your questions or requests, it is important to know that we categorize queries into two main types: "Summary Queries" and "Document Search Queries." The way we respond to these two categories of queries differs.
Query Categorization:
- Summary Queries: These are questions that require a written response, such as explaining a concept or providing information on a specific topic (e.g., "What is the role of mitochondrial fusion in cancer progression?").
- Document Search Queries: These are queries specifically requesting documents, such as research papers or publications on a particular subject or from a particular source (e.g., "What are publications from the University of Pennsylvania in 2015 on the topic of economics?").
Response Generation Process:
For both types of queries, the response is generated by following these steps:
- Retrieving Articles: We start by retrieving articles that exhibit the highest degree of semantic similarity to user query and complement them by adding articles with the utmost relevance through a keyword search. Research Assistant usually transform user queries into a structured document search.
- Organizing Articles: Once we have this collection of articles, we organize them in descending order according to their similarity scores to the query. The list of publications goes through a proprietary ranking algorithm. This algorithm further improves the relevancy of the top articles on the list, ensuring that the most relevant references are retrieved.
- TFormulating Response: Research Assistant uses the abstract content from the top 8 search results to generate a response to the query asked. The response may not leverage all 8 of the references listed. The research assistant chooses which information it requires to provide the best answer to the question
Response Types:
- Summary Queries: If the query falls under the category of "Overview Que-ries," we send a curated query to our summarizer tool that leverages the power of generative large language models (LLMs). This tool generates a response using trusted Web of Science content. The generated summary is then provided as the response to your query. This ensures that the information is reliable and up to date. References are included in the response for easy fact-checking.
Example queries:
- Summarize this article 'Oral stimulation for promoting oral feeding in preterm infants'
- Summarize DOI10.1016/j.biosystemseng.2022.06.013
- Document Search Queries: For "Document Search Queries," we return the 8 most relevant documents as a response to your query. This enables you to access specific research papers or publications that are closely related to your query.
Example queries:
- Papers published in 2018 on climate change mitigation
- How does climate change affect the migration patterns of Arctic bird species?
- Retrieve papers authored by David Kashatus.
How are Trends and Analytics responses generated for documents, institutions, and researchers?
Trends and Analytics responses are generated by running a search, then essentially performing "Analyze results" on the result set.
- Document: Enter a query in the input box and Research Assistant will respond with the most cited papers on a specific research topic in the last ‘X’ months or years.
Example queries:
- What are the most cited papers on machine translation in the last 6 months?
- What are the most cited papers on genetics in the last 12 months?
- Institution: Enter a query in the search bar and Research Assistant will respond with which institutions have published the most output in a given topic or research field.
Example queries:
- Which institutions published the most on climate change in the last 12 months?
- Which institutions publish the most on generative AI?
- Researcher: Enter your query in the search bar and Research Assistant will respond with the top researchers based on the number of publications and/or most cited in each topic.
- Example queries:
- Who are the top researchers in machine translation?
- Who has published the most in the field of cruciate ligament injury?
- Who are the most cited researchers in the field of soil sciences?
Seminal Papers
Seminal papers in each topic are foundational papers that provide a critical understanding of the origins and evolution of a given topic to support your research.
Enter your query in the input box and Research Assistant will respond with seminal, foundational, influential, critical, groundbreaking, historical, or pivotal papers.
Example queries:
- What are the seminal papers on child language acquisition?
- Are there any foundational papers on the history of democracy?
- I'm looking for historic papers on the role of women in the civil rights movement.
- Are there any groundbreaking papers on the development of robotics technology?
Visualizations
- Citation Network Visual: Enter your query in the search bar and Research Assistant will return 8 relevant references. Click the ‘view more’ button on the references and select ‘see related documents. Given a specific paper, Research Assistant will display a visual graph of connections to other papers by citation to identify clusters of closely or co-citing papers or distantly related papers.
- Topic Map: Given an identified topic within a search query, Research Assistant will display a topic map showing relationships between that topic and sub-topics or related topics.
- Publication Over Time Graph: Given an identified topic within a search query, Research Assistant will display a bar chart showing the output of publications (research documents) on that topic by year.
- Enriched Cited References
- Enter your query in the search bar and the Research Assistant will return 8 relevant references. Given a document or documents in a response from WoS RA that have enriched cited references, users can view papers which support, differ, discuss, or include these papers in their background. Users will be able to discover papers that cite these papers in differing contexts to build a more comprehensive view of the research to support their research question or literature review.
- Top Researchers/Researcher Profile Tiles for Top 5 Researchers
- When users click on a suggested button or prompt, they should easily access additional relevant research information including top 5 researchers, topic maps, related searches/follow-on questions, citation network map, and publication over time graphs specific to the topic and/or record.
Guided Tasks and Workflow
Guided workflows are context-specific prompts to help the user expand or narrow their discovery and complete defined tasks. Choose a guided task on the Research Assistant landing page depending on the research specific task you want to accomplish
- Understand a Topic: Click on ‘Understand a Topic’ workflow to start a conversation with the Research Assistant. The Research Assistant will begin by asking about your topic of interest or research question. Once you enter a topic, such as climate change, seminal or foundational papers related to that topic will be provided. You can view additional documents, explore a co-citation map for each returned article, or examine a topic map, publication timeline, or top authors related to the topic.
- Find a Journal (Manuscript Matcher): Click on the ‘Find a Journal’ workflow to initiate a conversation with the Research Assistant. The Research Assistant will start by asking for the title and abstract of your document. Once you provide this information, a list of the top 5 journals that match your title and abstract will be generated. You can then explore additional subjects, view a co-citation map for each returned article, or examine a topic map, publication timeline, or top authors related to the topic
- Literature Review: Click on the ‘Literature Review’ workflow to start a conversation with the Research Assistant. The Research Assistant will begin by asking for your research question. Once you provide this information, a topic map will be displayed. By clicking on the bubbles, foundational papers will be retrieved, along with 8 relevant papers already identified. You can then explore additional subjects, view a co-citation map for each returned article, or examine a topic map, publication timeline, or top authors related to the topic.
Guide for Writing Good Queries
To make the most of the Web of Science Research Assistant and effectively find answers and evaluate resources for your research questions, it's essential to craft well-structured queries. This guide will help you write good queries tailored to the tool's capabilities.
- Finding Documents or Document Sets: If your goal is to discover research papers or documents, consider the following guidelines:
- Be Specific: The more specific your query, the more precise the results. Clearly define what you're looking for.
- Provide Details: Include information such as institutions, regions, countries, and timeliness (years or asking for recent documents) to narrow down your search.
- Specify Subjects or Topics: Mention the subject or topic of interest to ensure relevant results. Use appropriate keywords.
- Use filters as your guide: Think about how you might refine or filter your search in Web of Science and provide this information so the response is as relevant as possible.
Examples:
Papers on biotechnology from the University of California from the years 2020-2023
Open access documents published in Economics in the year 1999
- Answering Academic or Scientific Questions: If you need precise answers backed by credible information and references, here's how to create suitable queries:
- Ask Specific Questions: Formulate clear and concise questions about academic or scientific topics.
- Seek In-Depth Information: Since this tool pulls from credible sources, you can ask questions that require in-depth and well-referenced responses.
Examples:
What is the role of mitochondria in cancer?
Difference between global warming and climate change?
Conclusion: By following these guidelines, you can maximize the effectiveness of the Web of Science Research Assistant. Craft precise and well-structured queries to obtain the most accurate and reliable information to support your research and academic effectiveness.
Types of questions WOSRA can answer - At Launch
| Question type | Example |
| Question-based search with summarization/answer |
What is the role of the mitochondrial fusion in cancer progression? What are the trends in climate change and global warming since ice age? |
| Article summarization by title | Summarize the paper titled 'The potential impact of droplet microfluidics in biology' |
| Article summarization by DOI | Summarize the ideas in DOI: 10.1126/science.1228026 |
| Article summarization by PubMed ID | |
| Document search by topic | Suggest some papers on climate change |
| Document search by institution name | Papers published on cell biology at Stanford |
| Document search by country | Give some papers on cell biology from Germany |
| Document search by citation count | List papers on cell biology with more than 100 citations |
| Document search by author name | Papers by Kashatus on cell biology |
| Document search by journal, issue, and volume | Search for papers with 20 citations or more on global warming published in Science volume 51, 658 |
| Document search by multiple entities |
Give some papers on biology from Germany |
|
Document search by recency, most/least citations
|
What are the most cited/recent papers on microfluidics? Can you find recent studies on manipulation in the media? |
| Document search by analytics (institutions, researchers) |
Which universities have the most publications in global warming? |
| Document search by seminal or foundational papers |
Show me seminal papers on climate change Are there any foundational papers on the history of art? Are there any groundbreaking papers on the development of clean energy sources? |
| Search in multiple languages |
妊娠高血壓產後血壓變化? 請收尋妊娠高血壓疾病與產後壓力及產後憂鬱的相關性 Necesito papers sobre la idea de negocio y la fase inicial de una business incubator найдите новейшие научные разработки русских ученых в химии
|
Types of questions Web of Science Research Assistant ‘cannot’ answer at launch, but considering for the future roadmap
| Feature/types of questions | Example |
| Search based on aggregation |
How many papers were published on microfluidics last month? How many research articles are published on mental health in 2022? What is the total number of my papers for citation? How many open access publications in University College Dublin? |
| Search by visualizations |
Show me publication over time graph for climate change Show me top map for language acquisition Show me co-citation map for article ‘X’ Publication over time graph for adult education |
| Search based on researcher profile data |
Who is John Smith from University of Manchester? Merge my two profiles into one profile |
| Search by H-index |
How is H-index of author ‘X’ compared to author ‘Y’? Which author has high H-index in environmental science? |
| Literature review |
Create a citation report for John Doe Create a citation report for research at Stanford Give me my citation report Make literature review about topic ‘X’ or ‘Y’ research title |
| Personalized query | Search history data, article recommendations. |
| Search memory |
Summarize article 3 from the last answers Don’t include ‘X’ title, topic or keyword based on my previous search I do not want to include ‘breathing’ in my retrieved articles relating to respiration |
| Search by complex queries | TS = Climate changes AND Global warming OR Rising sea levels OR deforestation NOT CU = US |