UOS Library AI Guide and Tools

AI Tools in the early stages of research

The initial steps in research involve developing ideas, reviewing existing studies, securing financial support and partnerships, and verifying the dependability of data sources. These actions create a framework for the research, ensuring it's based on prior knowledge while addressing new issues and setting the stage for its conclusion.

Literature Searches

Researchers often find the initial stages of research, particularly literature searches, to be very time-consuming and demanding. However, it's crucial to carefully examine a large amount of literature to identify relevant sources, verify that references reflect the most recent discoveries, and summarize information into a well-organized literature review.

Generative AI tools can accelerate and partially automate literature searches. A basic chatbot can suggest research areas, while specialized tools can organize relevant literature in a user-friendly manner, summarize lengthy and complex texts, identify key points, compare and contrast ideas, and even extract data

Experimental Design

AI tools can recommend possible sampling methods and experimental designs based on the research goals and subjects to assist in developing research methodologies.

AI tools researchers are using in the early stages:

Assistant by scite	An AI-powered for literature retrieval, validating output against an internal database.
Connected Papers	Visually maps connections between papers based on citation patterns.
RIS.AI	The product of an EU-funded project, it finds relevant papers, summarizes findings, identifies connections between different studies, and extracts data.
Nature Navigator	Tracking of research trends, summarizes articles, and identifies collaboration opportunities.
Perplexity	Summarizes complex documents, reducing reading time and making comprehending studies easier.
Research Rabbit	Explores topics of interest by suggesting related papers, tracking associated research trends, and organizing findings.
TDM	Automated process of selecting and analyzing large amounts of text or data resources for purposes such as searching, finding patterns, discovering relationships, semantic analysis.

AI tools in the Advanced stages of research

The intermediate stages of research involve conducting trials, experiments, gathering data, analyzing data, and writing the research manuscript. This phase is vital for generating empirical evidence that supports or contradicts the research hypotheses and preparing the work for publication. Many tools have existed for writing, even before ChatGPT, but recent advancements in machine learning and AI have significantly improved their capabilities.

Working with data

AI tools can automate data organization tasks, surpassing human capabilities in data analysis. They can correct errors, enhance writing style, and streamline repetitive tasks. By automating data accuracy checks for trials, experiments, and data collection, AI tools can improve data quality. Additionally, they offer advanced analytics features, enabling researchers to discover insights that might be overlooked in manual analysis.

Drafting Papers

Writing research papers, especially for those whose primary language is not English, can be a time-consuming and challenging process. Many researchers seek to expedite this task. However, the use of AI tools for writing research papers remains a controversial topic.

While AI tools can be valuable aids in writing research papers, researchers must exercise caution regarding the output. Often, the generated content requires further refinement to ensure its suitability. It's essential to integrate AI-driven insights within a comprehensive analytical framework, combining the strengths of AI with human oversight to guarantee accuracy and relevance.

Finding Suitable Journals

Selecting the right journal can significantly impact the revision process and a researcher's publication record. While some experts recommend choosing a target journal early on, many researchers defer this decision until later in the process.

AI-powered journal finders can assist researchers in identifying appropriate journals for their work.

Manuscript Preparation

Once a journal is selected, preparing a manuscript for submission requires meticulous attention to detail to adhere to formatting, citation, and submission guidelines.

AI tools can streamline these late-stage activities by automating many time-consuming tasks. For instance, AI can assist in formatting manuscripts according to journal guidelines, checking citations, and ensuring adherence to style guides. AI-driven plagiarism detection tools can scan manuscripts to identify any unintentional similarities with existing work, helping researchers maintain the originality of their submissions.

It's crucial to remember that AI tools should not be used as a shortcut. While they can be valuable aids, human oversight remains essential to address field-specific nuances that AI might overlook. Combining AI-driven insights with manual review is key to producing high-quality work.

AI tools researchers are using in the advanced staged:

AudioPen	Converts voice notes into text that's easy to read and ready to share.
ChatGPT	Helps get answers, find inspiration and be more productive.
Claude	Processes large amounts of information, brainstorms ideas, generates text and code.
Dante	Assists with data analysis and visualization, providing recommendations based on complex datasets.
Gemini Pro	Recalls on long-context retrieval tasks across modalities, unlocking the ability to accurately process large-scale documents, thousands of lines of code, hours of audio, video.
Grammarly	Well-known writing assistant that checks for grammar and readability.
Jenni	Writing assistant to enhance academic and content writing.
Microsoft Dictate	Uses speech-to-text to author content in Office with a microphone and reliable internet connection.
Mistral	Provides a fine-tuning API through La Plateforme, making it easy to fine-tune our open-source and commercial models.
Quillbot	Writing assistant for paraphrasing, summarizing, and improving writing.
Paperpal	A generative AI-powered academic writing tool.
Research Round-Ups	Literature Reviews generated through a human-machine collaboration.
Tableau	Business-oriented data visualization tool for analyzing and presenting data.
Penelope.ai	Helps authors satisfy journal requirements.
Jane (journal author name selector), Journal Selection dashboard  and MY journal selector	Journals Finder Websites.
Copyscape	Plagiarism detection tool that scans text for duplicate content and reports on potential matches.
Snapp	A peer review system that enhances the efficiency of the publishing process.