New AI tool in Virtual Library

Research Assistant. The University’s Virtual Library (accessed via University email log in) has implemented the “Research Assistant”, a tool based on generative artificial intelligence (AI) that uses large-scale language models (LLM). It allows you explore academic content by asking questions in natural language. The tool uses most of the content found in your library to identify five documents that can help answer your question. It then extracts the most relevant information from the description/abstracts of each source to write the answer. Below the answer, you’ll see the sources used to generate it along with in-line citations that let you clearly see which source was used to generate each part in the answer. Use these sources to delve deeper into the topic and to fact check the responses from the tool.

The Research Assistant is not a replacement for human expertise but uses artificial intelligence to automate otherwise time-consuming tasks. We’ve designed the Research Assistant make it easier to understand topics, their context, and resources published about it. Use the “view more results in your library search” button to find more documents relevant to your question. Click the AI-generated “related research questions” to explore topics similar to your question.

How are responses generated? Your question is converted into a query that the search engine understands with the help of a Large Language Model (currently GPT 3.5). The search engine then identifies the most relevant documents in the index. It ranks them according to how well they can answer the question and, again a with the help of the Large Language Model, creates an answer from the top 5 sources. Due to the nature of Large Language Models, answers to the same question are not always the same. There may be more than one possible answer and different resources that are relevant. If you are not satisfied with your answers, use the “Try again” button.

How to formulate a good question? To make the most of the Research Assistant, it’s essential to ask clear and detailed questions about academic or scientific topics. Be as specific as possible and phrase your query in the form of a question. Example queries can be found on the starting screen.

Supported questions/instructions. The Research Assistant supports local language searches. Most material in our index is in English. If you ask a question in another language than English, the Assistant will search in both, your local language and English, and write the answer in the language of your question. Note that there is a dependency on the Large Language Model and language support may vary. We are currently using GPT 3.5 for language processing and translation. You can add language-specific instructions to your question just as you can in ChatGPT. For example, you can add “answer in German” or “answer in French” to the end of your research question.

Unsupported questions/instructions. Some instructions are not currently supported by the Research Assistant, like requests for materials of a particular type (e.g. “give me peer reviewed articles about bird migration”) or from a certain time period (e.g. “give me the newest research on climate change”). You will still receive an answer when including these instructions and the ranking algorithm will take keywords like “peer-reviewed” into account, but the tool will not filter content by type or date. The Research Assistant does not yet support follow-up questions. Each question stands by itself. For example, if you ask “what topics did Simone de Beauvoir write about”, you cannot follow up by asking “and what is the content of that work” and expect the system to understand what you mean. At this time, you will have to include all relevant information in each question, e.g. “what is the content of Beauvoir’s The Second Sex”?

Video presentation on “Science Assistant”

Web of Science Research Assistant is on trial

The Web of Science Research Assistant is a generative AI-powered tool that enhances your research. The assistant is designed to keep up with your research needs as they develop. Research Assistant is situated in the middle of top bar of Web of Science.

The access for the University community is valid to 20 October, 2024.

Learn more about the Web of Science Research Assistant here

English-Corpora.org subscription

English-Corpora.org are a collection of highly curated corpora (or collections of text) designed for searching text from a range of resources to observe language, variation, and change between specified dates on specific items. These online corpora are used for many different purposes by teachers and researchers at universities throughout the world. The corpus data (e.g. full-text, word frequency) are used especially in language learning.

Training Sessions on “How to Publish with Oxford Journals”

These sessions will help you determine whether you are ready to publish your work, the following topics will be discussed :

Differences between a thesis and an article
How to write a manuscript
Types of journal manuscripts
How to select which journal you want to write for
OUP & DORA – Journal metrics in the context of how they’re calculated
Initiative for Open Citations (I4OC).
Credit Taxonomy – Levels as a Researcher
How do you upload a manuscript on the OUP platform – Article submission process
The journal publishing cycle
What is Open Access – Kinds of Open Access
Understanding Read & Publish – How it benefits your Institution

Sep 19 th, 2024 (10:30 AM–12:30 PM) Register

Sep 26 th, 2024 (10:30 AM–12:30 PM) Register

Trial access to EBSCO literary criticism databases

The trial access to selected EBSCO Literary databases has been activated and resources are now available in test access for academic community of Vytautas Magnus University:

LitBase

LitBase database supports literary research on the most widely studied authors, poetry, fiction, plays, and nonfiction worldwide, providing resources such as author interviews, bibliographies, biographies, book reviews, classic books, encyclopedias and dictionaries, nonfiction, full-text journals, literary criticism, novellas, plays, poems, short stories, and more. LitBase provides more author interviews, biographies, creative nonfiction, literary criticism, poems, poetry reviews, screenplays, and short stories from antiquity to the 21st century, including works of high culture not produced in the West. Among its 1.5 million records, users will find historical and contemporary texts from around the world, including Africa, Australia, Canada, the Caribbean, Europe, Ireland, Latin America, New Zealand, Scandinavia, the Slavic countries, the United Kingdom, and the United States.

Literary Reference Source eBook Subscription

Additional database to LitBase, containing reference works covering a wide range of literature-related topics, including literary criticism and guides to the study of classic literature.

The databases were added to EBSCOhost platform at https://search.ebscohost.com/ and are available for end users directly within the network of IP addresses and remotely, from home computers and mobile devices.

The access for the University community is valid to 8 November, 2024.

Online session dedicated to LitBase

NEW! LitBase

18th September 2024, 11:00 AM EEST (40 minutes) | Register

Trial access to PressReader (newspapers and magazines database)

PressReader has the largest selection of newspapers and magazines from over 120 countries in over 60 languages. That’s 7,000 trusted publications on a single platform: global news from the world’s most reputable journalists and sources from The Washington Post, The Guardian, Le Figaro, Forbes, National Geographic, GQ, Vogue, Harper‘s Bazaar, etc.

The access for the University community is valid to 7 October, 2024.

Oxsico has become Identific

Educational technology start-up Oxsico has changed its name to Identific. The change was prompted by a change in service profile, such as the addition of artificial intelligence recognition, and the supplier’s desire to more clearly communicate the company’s core values. The news release states: “The word “Identific” conveys the problem areas identified during the training process and the corresponding corrections in response to the marked areas. Therefore, with the new name, we will present a different approach to the plagiarism prevention process as well as new functionality. The system will become an educational tool, making it easier for students to understand and correct mistakes, reducing stress and saving time and administrative burden for lecturers and university administrators.”

All changes will be made within the system. User logins will remain the same, but users should use the identific.com environment to connect to the system.

EBSCO online sessions September 2024

Registrations for the training cycle organized by EBSCO designed for librarians, researchers, teachers and students, who would like to learn more about EBSCO.

EBSCOhost in a NEW version!

10th September 2024, 2:00 PM EEST (60 minutes) | Register

During the session, we will review the new interface of the EBSCOhost platform, which allows searching in subscribed EBSCO databases. Our user experience team has spent years observing students and the challenges they face when using library interfaces. The result is a new EBSCOhost interface to meet ever-changing user expectations. Join the session if you are curious what the updated version of your favorite platform looks like.

Everything that you should know about EBSCO Mobile App

12th September 2024, 1:30 PM EEST (30 minutes) | Register

Overview of the features available in the new EBSCO Mobile App. We will show you how to download, log in and use the application. We will tell you how to download an e-books within the app. All in just 30 minutes.

NEW! LitBase

18th September 2024, 11:00 AM EEST (40 minutes) | Register

LitBase is a database of selected critical texts on literature. It supports research on the most studied authors, poetry, fiction, plays and non-fiction works worldwide. Take part in the training and learn in detail about the content of the database and how to search within the resources.

EBSCO eBooks in practice!

19th September 2024, 1:00 PM EEST (40 minutes) | Register

Practical training during which participants will learn how to use EBSCO eBooks online, how to download full e-books and chapters, how to use e-books on smartphones, tablets and readers and how to download and authorize Adobe Digital Editions.

Searching with Education Source Ultimate

23rd September 2024, 12:30 PM EEST (45 minutes) | Register

During the session, we will review the most important resources available in Education Source Ultimate, a database released in a new version in June 2023. The session will mainly be a search workshop, during which we will present several practical examples of searching for scientific materials in the field of education.

JSTOR Research Webinar

Thursday, September 5 at 8:00 PM EDT

Learn about the latest time-saving features and functionality on JSTOR. These make finding, keeping track of, and sharing all kinds of content on JSTOR easy and efficient.

Explore:

– new and more efficient ways to discover books, journals, and research reports;
– how to unearth millions of primary sources from contributing collections including audio and video files;
– finding and saving Images from museums and collections worldwide;
– updates to the JSTOR Workspace, the place to organize and share content on JSTOR.

Registration

Happy Science and Knowledge Day!

Knowledge is the greatest wealth. May knowledge and the ability to use it become a constant necessity in life, give you confidence and open up new opportunities to achieve your dreams and life goals!