Category Archives: Innovation & Technology

Use of AI technologies in databases

AI technologies are increasingly being integrated in scientific databases. We have summarized the advantages and disadvantages of AI technologies in databases and explain, how this option can be used effectively.

In addition to content summaries and the in-depth exploration of documents, the use of AI in scientific databases also involves a Natural Language Search (NLS). This search mode is an (optional) component of the Simple or Advanced Search and allows search queries to be formulated in everyday language.

The NLS mode uses Natural Language Understanding (NLU) to understand the intent and contextual clues in a query. This function is particularly beneficial for less experienced database users.

As an example, we have tested the use of Natural Language Search in the Ebsco database Academic Search Premier. In addition to the usual search modes, you can also select NLS in the simple search.

The query entered is displayed above the result list as a search string with linked search terms (show refined query). However, the search is only carried out within simple search mode, which means that important search results could be overlooked. An advanced search provides a more detailed overview.

Due to the simple search mode, formal search criteria or filters are not recognized at the moment. Here are two examples of NLS search queries and their counterparts.

Example 1: “Show all articles from 2020 that contain the keyword automation in the abstract”. This is transformed into a search string as follows: automation AND (abstract) AND (2020).

Example 2: “I need articles on climate change that were published between 2020 and today for a research paper I am writing” is transformed into the search string: ((climate change OR global warming) AND (article OR research) AND (2020 OR 2021 OR 2022 OR 2023)).

Filters such as “Source Type” or “Publication Date” are not recognized. Furthermore, in example 2, the time period is not set to include 2024 or 2025, although the keyword “today” was used. It could be due to the status of the training data for the AI. This can also lead to important search results being overlooked.

The NLS search finds a maximum of two alternative search terms for one search aspect. Deeper filtering, e.g. to limit results to articles from a specific journal (publication), is not possible in the NLS.

Of course, AI technologies in databases are constantly evolving, so this information can quickly become outdated.

Another database that uses AI technology to support the research process is Statista. Here, the “Research AI” tab offers the option to search in natural language (except for the content of Consumer Insights and Company Insights). There are examples of prompts that can help you to interact effectively with the AI. In Statista, the results found are summarized by the Large Language Model (LLM) Claude 3 Sonnet and the sources used are indicated below the summary.

Unfortunately, this database does not provide the search terms to track how and where searches were carried out. Possible follow-up questions are suggested to users for further exploration of the topic.

Other databases that already use AI to support searches are Web of Science (Smart Search: free of charge & already available; Web of Science Research Assistant: fee-based, not yet included in the license), ScienceDirect (ScienceDirect AI: fee-based, not yet included in the license) and Scopus (Scopus AI, fee-based, not yet included in the license).

The rules of prompting (entering a query) can also be helpful for database searches. In particular, the query should be formulated clearly and precisely and avoid unnecessary filler words.

As this topic is highly discussed and very much evolving, information can quickly become outdated. Please also check the websites of the providers mentioned and contact our information desk if you have any questions.

Further information can be found here:

https://www.tu-chemnitz.de/ub/kurse-und-e-learning/elearning/studierende/mika/darstellen_mit_ki-tools.html#anwendung

https://www.ub.ruhr-uni-bochum.de/recherchieren/rechercheleitfaden/wissenschaftliches-recherchieren-mit-ki-tools

OpenAlex: a free alternative to Scopus and Web of Science?

Scientific research tools such as Scopus, Web of Science or Dimensions have now become established. Many researchers have stored complex search queries in their favourite database. However, the cost of these platforms is a significant item in the budgets of libraries and research institutions.

What if there was a bold, free alternative to these expensive tools? Actually, there is, and there has been for some time, but only recently has it started to gain traction: OpenAlex.

OpenAlex can be defined as “a fully open catalogue of the global research system”. It has been maintained by OurResearch since around mid-2021 and the data comes from the Microsoft Academic Graph, Crossref, institutional repositories (via OAI-PMH) and much more. OpenAlex has access to a large amount of data and is based on persistent IDs (DOIs, ORCID, ROR, etc.).

Don’t be fooled by the minimalist interface and the absence of corporate design colours. OpenAlex concentrates on the essentials and does its job very well. Until a few months ago, queries could only be made via the API. Now it has a graphical user interface that is constantly being updated and improved. I have an account where I can save my queries. I find it simple and useful, but perhaps it is still too little for a researcher. However, development continues.

I then ran some tests and entered the name of TU Chemnitz to see the results:

Here the results from Scopus:

Very good. We have about 6,000 more results than Scopus. However, this does not mean that all the works displayed are actually related to Chemnitz University of Technology. Quality control still needs to be improved in OpenAlex. However, I was also impressed by the presence of some graphics.

If you are a researcher, I invite you to enter your name in OpenAlex and check that all the data is correct. It is also possible to calculate your own H-index with this script in Jupyter Notebook (if you need help, write to me).

I also tested this script, which uses the data from OpenAlex to show which co-operations TU Chemnitz has with other universities worldwide. Here is the result:

This is only a first approach to OpenAlex, and it is necessary to deepen the knowledge of the data structure and quality control. There is a lot of potential in it and its possibilities are currently limited, but it is an interesting project and it is worth giving it a chance.

Why your research career needs a Persistent Identifier

A Persistent Identifier is a kind of number plate that we wear in the web. After all, we use PIDs on a daily basis in our analogue world, such as when we are asked for our identity card number. Only here we are on the web. Fortunately behind a Persistent ID there is an organization that ensures its persistence over time. At this point someone might reply that the address of a website is a persistent ID. Wrong, because behind it there is not always an association to ensure its long-term durability.

A PID is “a code which remains constant as a means of identifying a digital object regardless of changes to its location on the internet”.

 

Den Beitrag weiterlesen Why your research career needs a Persistent Identifier

Introduction of and to the new central University Library

Foto: Annett Kittner

On October 1, 2020 it will finally happen: The new central University Library will open its doors to the public after a period of reconstruction of more than five years in the building of the “Old Spinning Mill” at Straße der Nationen 33.
Den Beitrag weiterlesen Introduction of and to the new central University Library