Tracking Sustainable Development Goals using Symplectic Elements

During Symplectic’s 2023 North American User Day, Alexandra Hiniker (Director of the Sustainability Initiative) and Jason Glenn (Program Director for Research Information Management Services) presented on CMU’s Sustainability Initiative and how they have been utilising Elements to help track their researchers’ engagement with and outputs related to the 17 Sustainable Development Goals, a set of global objectives agreed to by all countries the United Nations as part of the 2030 Agenda for Sustainable Development.

The post Case Study: Carnegie Mellon University appeared first on Digital Science.

At Digital Science, we recognize that the journey toward AI adoption is as unique as the organizations and individuals we support. From bench researchers to medical affairs professionals to research offices, our approach is grounded in collaboration and deep understanding.

Since 2013, we’ve been investing in advanced AI methodologies, expanding our technical and analytical capabilities, and assembling a global team of AI experts. To us,  AI isn’t a one-size-fits-all solution; it encapsulates a range of both new and existing capabilities and approaches that when thoughtfully applied, can significantly enhance capabilities and streamline workflows. Our commitment continues to be focused on working closely with our partners, deeply understanding their unique challenges and aspirations, to deliver innovative and responsible AI capabilities that enhance human intelligence, drive progress, and unlock the full potential of the research community.

Our Capabilities

For the last decade, we have focused around machine learning innovations with Dimensions.ai, investment in Writefull and development of different LLMs. Building on this AI lineage, 2024 will see a continuous flow of new releases, starting with Dimensions Research GPT Enterprise and Dimensions Research GPT.

Dimensions in ChatGPT

Available via OpenAI’s GPT Store, the new products aim to provide users looking to use ChatGPT for research-related questions with generative answers they can trust – grounded in scientific evidence from Digital Science’s Dimensions database.

Key features of Dimensions Research GPT Enterprise – available to Dimensions customers with a ChatGPT Enterprise licence – include: 

• Answers to research queries with publication data, clinical trials, patents and grant information
• Set up in the client’s private environment and only available to client’s end users
• Notifications each time content generated is based on Dimensions data, with references and citation details
• Possible for clients to have custom features (following prior discussion with Dimensions).

For Dimensions Research GPT, answers to research queries are linked to tens of millions Open Access publications, and access to the solution is free to anyone with a Plus or Enterprise subscription to OpenAI’s GPT Store.

Next-generation search experience

Dimensions has introduced a new summarization feature [need link] to support the user in their discovery process for publications, grants, patents and clinical trials. It has integrated AI-driven summarization capabilities into the Dimensions web application to enable all users to accelerate the identification of the most relevant content for their research questions. Short, concise summaries are now available for every record in a given search result list with a single click, providing users with AI-generated insights quickly. The Dimensions team has used feedback from members of the research community – including academic institutions, industry, publishers, government, and funders – to develop this summarization feature in the Dimensions web app.

Smarter searching in Dimensions

Other AI solutions will follow shortly from Digital Science, all of which seek to surface AI capabilities to support users with specific, relevant functionalities where AI in particular can offer improved results. Just as importantly, they have been developed with a grounding in reliability and responsibility so that users can trust them as they do with all our other products. 

Connecting your Data

The Dimensions Knowledge Graph, powered by metaphactory, aims at helping customers harness the synergy of global research knowledge and their internal data, and enable AI-powered applications and business decisions.

AI-Powered Writing Support

Writefull uses big data and Artificial Intelligence to boost academic writing. With language models trained on millions of journal articles, it provides the best automated language feedback to date leading the next generation of research writing help.

Deeper Understanding of Scholarly Papers

Available within ReadCube Enterprise Literature Management & Papers Reference Management, our beta AI Assistant is designed to enhance research efficiency by providing real-time, in-depth analysis, summarization, and contextual understanding of scholarly articles within a researcher’s literature library.

Our latest AI insights

An experienced partner in AI

The history of AI at Digital Science

Discover

AI & Digital Science

How does Digital Science use AI? We ask ChatGPT

Find out

The post Digital Science and Artificial Intelligence appeared first on Digital Science.

One of the world’s largest scientific societies and the premier home of chemistry professionals publishes over 80 journals spanning all disciplines of the chemical sciences.

The society’s Production Operations team is responsible for tasks like technical editing and proof review. As the organization grew, it needed more capacity, and they now leverage a global supply chain – including Writefull.

The team is also involved in developing and implementing new technologies, with a particular focus on how to make the best use of Artificial Intelligence. They looked into the concept of language modification done programmatically but were “really striking out with commercially available broad-sweeping tools. They did not perform well on our content.” What they needed was something that could suggest improvements to academic language usage, such as sentence structures in scientific writing or discipline-specific vocabulary. 

Supporting the entire publishing workflow

Then the organization was introduced to Writefull. They were immediately intrigued by the specificity it offers, as Writefull’s models can be tailored to a particular niche of scientific content. After a competitive RFP process, they decided to work with Writefull, and together they began developing some of the services they have since operationalized. 

Writefull’s full publisher solution offering supports each stage of the publishing pipeline, from submission to copy editing to quality assurance:

Over the years, the society has incorporated four unique tools from Writefull. A member of the Production Operations team explains: “We have a very rigorous method for evaluating the quality of each step of the production process. For example, one of the things we need to do when we evaluate quality involves scoring the language after copyediting. Traditionally, it would take a long time for one of our team members to complete a review like this, limiting the amount of content that could undergo quality review. But when we tailored Writefull’s Manuscript Categorization API to our requirements and benchmarked it against our own quality analysts, it reached over 95% alignment in categorising texts.” With such a high level of alignment, the automation of this task can significantly reduce the time spent on manuscript evaluation and allow more content to be reviewed for quality purposes.

The organization’s quality evaluation program also includes assessment of metrics such as whether author names and affiliations are present and correct. They use Writefull’s Metadata API to facilitate and partly automate this task, by extracting manuscript elements for post-editing quality assessment. This reduces the number of items in their quality evaluation that need manual review and the time spent reviewing them.

Another API they have adopted is Language Edit Assist (LEA), which auto-applies a highly customized subset of Writefull’s language edits to manuscripts prior to copyediting. The manuscript is then at a better starting point when it reaches the copyeditor, increasing efficiency in the editing process.

A transformative step

Writefull’s services have delivered multiple benefits to the society – including demonstrable time and cost savings. 

A prime example comes from its recent analysis of LEA results. 715 papers were randomly split into two workflows, with manuscripts of similar language quality levels present in each workflow. Prior to technical editing, one group had automatic edits applied by Writefull’s LEA service and the other group did not. Without LEA applied, 58% of the papers were classified as well-written (the highest quality level). But with LEA applied, 81% of the papers were classified as well-written – enabling the organization’s copyeditors to focus their time on high-value-added edits, instead of on basic grammatical fixes, such as articles, punctuation, and conjunctions.

Additionally, editors at the society evaluated 35,000 individual edits made by LEA. After refinement using internal data, edits applied without error were 99.04%, and edits introducing errors were 0.96% – showing a high level of accuracy.

“It has been transformative,” says a member of the Production Operations team. “The data we’ve obtained has really been useful because it’s highly customized to our work. Having quality information at the right time is so important, and there’s a limit to what human manual efforts can do and when they can do it. Being able to do it programmatically with a high degree of accuracy gives you a wealth of data – and that means you get new insights into how you’re operating the business and the strategic directions you should consider.”

From strength to strength

There has been a high degree of adoption, and the society and Writefull are working together to refine the processes further. 

They are now looking ahead at what this adoption and their new knowledge means for operational performance: “Is there some opportunity there for improving throughput or quality? What are the key metrics that this is going to impact? The next part is to manage that forward. We’re seeing the refinements boost the tools’ overall performance and increase staff buy-in further.”

Part of the project’s success is attributed to how well the organization and Writefull work together. Juan Castro, CEO and Co-founder of Writefull, reflects: “Many of the services we offer to publishers today are the fruits of our collaboration with this society. It is together that we have identified challenges, thought of solutions, and developed and vetted new technologies. I personally think LEA is the most exciting of all—it is such a powerful solution, which offers direct assistance. We look forward to many more future projects together.“

The society has found Juan and the wider Writefull team to be “very creative and collaborative, and they’ve really been engaged in coming up with innovative ways to overcome the challenges involved and achieve our goals. They’re a fantastic group to work with.”

If you’d like to explore how Writefull’s services could support your organization, request a demo. 

The post Writefull Case Study appeared first on Digital Science.

11th February marks the annual International Day of Women and Girls in Science, celebrating the achievements of women in science, technology, engineering and maths (STEM) professions, and encouraging girls in school to pursue STEM-related subjects with a view to contributing to STEM-related careers.  Set up by the United Nations in 2015, the aim is to expand the pool of talented researchers and tackle gender disparity within STEM subjects. Digital Science believes in the importance of inclusive research, encouraging diverse perspectives and giving equal opportunities regardless of gender, race, ethnicity, or other dividing factors. Here you’ll find resources to shine a light on some of the issues as well as hear from others about ways in which they are supporting women and girls to progress in science.

Our aim is to bridge the divides and help get more women working in these fields in order to harness all talent in tackling challenges and driving progress for all.

New and thought-provoking research

A generational shift in reverse

For decades, the proportion of women publishing their first academic publication has increased. However, following the COVID-19 pandemic, this growth has gone in reverse for two consecutive years, with 2024 not looking better.

Read more

Sharing research and knowledge from a range of Digital Science experts highlighting, and celebrating the achievements of women in science, technology, engineering and maths (STEM).

Celebrating the women of TL;DR from Digital Science

Read

Rita Levi-Montalcini: A long life of achievement

Read

Elsie Widdowson: Long-lasting impact on health

Read

The Digital Science Speaker Series welcomes some of the most exciting and innovative movers, shakers, and doers from our research community

Our second Digital Science Speaker Series talk was from Professor Dame Athene Donald on how a career in science, technology, engineering or maths (STEM) is “Not Just For The Boys”, and how an underrepresentation of any group of society can impact the research being done.

Athene chatted with Digital Science’s Director of Researcher and Community Engagement, Dr Suze Kundu, about her research, her book, her experiences of being a woman in STEM, and the big changes she would like to see in research culture to foster greater inclusion of all genders in the STEM workforce.

Check out the video and the entire Speaker Series playlist over on YouTube. Don’t miss the TL;DR article about empowering women in STEM.

How else we are helping #BridgingTheDivides

In this TL;DR series we ask if a fragmented research ecosystem is slowing global progress?

The post Bridging the Divides for Women and Girls in Science appeared first on Digital Science.

Worldwide Cancer Research

The Practicalities of Partnership

Worldwide Cancer Research was the first Grant Tracker client, and has used the platform since 2011 to manage its full grants lifecycle. During the 2023 User Day in London, we heard from Peter Fisher, Research Funding Manager at Worldwide Cancer Research, on the practicalities of partnership and how Grant Tracker can be used to identify, manage and track joint funding initiatives.

This case study covers:

• How Worldwide Cancer Research uses Symplectic Grant Tracker to identify suitable projects for partnerships.
• Storing, tracking and monitoring contracts and legal arrangements with multiple partners across international borders.
• Monitoring finances, invoicing and payments and maintaining a comprehensive record across financial interactions.

Download the report

The post Worldwide Cancer Research appeared first on Digital Science.

The history of AI at Digital Science

While 2023 has been all about artificial intelligence (AI) and its future capabilities, the technology has been progressing for several years with Digital Science at the forefront as an established partner for its many communities. As part of the Digital Science #MindTheTrustGap campaign, Simon Linacre presents an overview of how Digital Science has developed its capabilities in AI.

For anyone who has been involved in academia for the past 25 years or so, they will remember the challenges that have followed from leaps forward in technology. How were we going to cope if the Millennium Bug crashed our machines on 1 January 2000? What would Web 2.0 mean for scholarly communications? Would MOOCs bring down the university as a learning institution?

All these big questions came and went without too much fuss in the end, showing how resilient scientific communities were in solving any problems that had arisen. In 2023, the Next Big Thing is of course AI – or more specifically, Generative AI that has been released on a mostly free basis to the world – and many people involved in research are pondering how it might impact them. 

Over the years, Digital Science has aimed to support researchers and research organizations in its early adoption and implementation of AI and AI-related technologies, such as machine learning (ML), natural language processing (NLP) and more recently large language models (LLMs). For a review of how Digital Science has supported research communities – and a refresher on what these and other AI-related terms mean – we have collated some of the key articles we have published in the last few years to guide people through the AI maze. From universities to pharmaceutical firms, from researchers to publishers, these articles look specifically not just at technology like NLP itself, but its applications and implications as well.

AI across different sectors

If you are working in a large corporate setting such as a pharmaceutical firm, AI will already be familiar to you. Nevertheless, some of the advancements using AI in recent years to support scientists have been nothing short of breathtaking. It has had a major impact on cancer research and detection, which was already apparent from this article in 2018; part of this has been the creation of huge knowledge bases such as Dimensions and devising tools to interrogate them to produce new knowledge and procedures. For example, as this post by Suze Kundu highlighted, technologies such as natural language processing could help identify specific information from huge amounts of unstructured data.

When Digital Science celebrated its 10th anniversary in 2020, one thing author Katy Alexander thought would be significant was that AI would enable both an increase in accessibility and ability to understand research across disciplines and themes in a much more structured way. We are seeing this play out already with the advancement of things like the Sustainable Development Goals (SDGs), and in turn AI is playing a part in enabling collaboration among academic researchers. 

Understanding how all these factors fit together and developing solutions that enable improved capabilities for researchers is at the heart of many academic publishers, who have felt the impact of AI in recent years most keenly. Five years ago we reported – somewhat prophetically – how machines were being revolutionized by AI and what the implications might be for academic publishers as automated text generation (ATG) had clear implications for creating article content. Further implications for publishing were also discussed by Suze Kundu with a look at the potential use of NLP in peer review, and the inevitable implications that would have on trust. As we have seen in the Digital Science campaign on trust with posts such as Daniel Hook’s on the ‘Lone Banana Problem’, while there are incredible advantages to be had from using AI, there are also disadvantages if the technology isn’t engineered well or if the user doesn’t account for potential errors.

Applications

When it comes to the application of AI technology, this is where the concept of a trusted partner is particularly important. When as individuals we use technology, we do so with implicit trust in the tool we are using – trusting it will work for us, that it will find the right results and that it won’t break any rules in doing so. Scale that up to organizations using hugely powerful tools across hundreds of individuals, then the trust in the technology partner also grows along with it. 

At Digital Science, we take the responsibility of being a trusted partner for customers and users very seriously, and one way we do this is in how we invest in future solutions for the research communities we work with. You can see this with the annual program we have had, known as Catalyst Grant. This showcased new technology in this space and led to a number of long-term investments, which in turn led to some companies becoming part of the Digital Science family. They have also included support for AI technology, such as two winners that sought to disrupt their niches in the research industry as highlighted in a piece by Alex Jackson. 

In his article on NLP and startups, Digital Science Director of Portfolio Development Steve Scott outlined what a key role NLP was already playing in Digital Science solutions, as well as their increasing value in the future. Rather prophetically he said, “In the next 10 years, we will see NLP capabilities expand and be embedded in new products and services, helping researchers navigate ever-expanding data outputs and allowing new ways to extract and interpret meaningful analysis from past and present papers.” Only we are seeing this much quicker than the 10 years Steve forecast.

Natural Language Programming

A key aspect of AI technology that Digital Science has focused on over the years has been NLP – so much so that we published a series of articles curated by Suze Kundu devoted to the topic. As well as asking – and answering – important questions such as ‘what is NLP’ posed by Suze, the series also looked at how NLP could assist in academic writing, which we have seen develop further with the Writefull solution for Digital Science. 

Another focus for NLP at Digital Science has been using AI as a force for good, mitigating against its risks for some communities in the future. This includes its use in product development for companies such as Scismic, where it has led the way in responsible recruitment, as well as Suze’s highlighting what the risks can be if certain warnings are not heeded. This is true right up until the present day as these risks are balanced in current AI technology developments at Digital Science, and we work to inform people about how what we witness with AI is not magic, but a science that requires high levels of skill and mastery as Daniel Hook so vividly portrayed in his article. 

Digital Science continues to work hard to achieve this – sometimes a little too hard. Despite our best efforts, we fooled no one on 1 April 2017 with ‘news’ of a new member of the leadership team, but who knows what might happen in the future?

The post Digital Science: An Experienced Partner in AI appeared first on Digital Science.

The year 2023 will forever be remembered as the year that AI finally broke into the mainstream. But in the research ecosystem, what do we mean by AI and how is it already being used? Simon Linacre does what everyone has been doing and asks AI itself for some answers

Anyone would be forgiven for thinking that artificial intelligence (AI) had only just been invented given the huge interest that has suddenly been generated in it in 2023. However, AI actually has a long history, being first conceived of in the 1950s and gradually becoming a reality in the decades after. Nevertheless, a real step forward has been made with Generative AI, which can create seemingly flawless text or images in just seconds. But is it really that new?

Writing these words on a Google Doc, I have already accepted one or two suggestions from the predictive text function, itself a form of AI. When you realize that the words you have chosen have not 100% been your own, you can see how lines have started to blur with the more advanced Generative AI’s capabilities. However, caution must still be used as AI is more than capable of getting things wrong – just read Digital Science’s post on ‘The Lone Banana Problem’. Moreover, a lack of context or key detail can lead to misrepresentation or redundancy in the content being created.

Digital Science and AI

Digital Science has been using AI and related technologies such as Machine Learning (ML) and Natural Language Processing (NLP) for several years now – indeed, Dimensions has had https://www.dimensions.ai as its URL since its launch in 2018 – and it has become a trusted partner for hundreds of organizations that depend on its AI expertise. These are the ways Digital Science and its portfolio companies uses AI-related technologies in 2023:

Dimensions

• Document classification; Researcher Disambiguation; Research Integrity Trust Markers

OntoChem

• Image classification to decide whether an image shows a chemical compound; Entity recognition to decide whether a term describes a chemical compound

ReadCube

• Sentiment Analysis for Mentions; Article Recommendation Engine

metaphacts

• Knowledge Graph and graph-based reasoning

Writefull

• Core writing assistance offering is AI-based; AI detection

Ask ChatGPT

The information above is correct because, well, I work at Digital Science and I know it to be true. It also breaks the information down by constituent parts in terms of each Digital Science company and how it uses the relevant technology. So what happens if we ask a Generative AI model how Digital Science uses AI? Well, we get the text below courtesy of OpenAI’s new ChatGPT iPhone app:

“Digital Science, as a company that provides scientific software and research solutions, utilizes AI in various ways. Here are a few examples:

• – Text and data mining: AI algorithms are employed to analyze large volumes of scientific literature, extracting valuable insights, identifying trends, and accelerating the discovery process.
• – Natural Language Processing (NLP): Digital Science uses NLP techniques to enhance the understanding and processing of scientific texts, enabling advanced search capabilities, automatic categorization, and semantic analysis.
• – Predictive analytics: AI models are trained on scientific data to predict outcomes, such as the success or impact of research projects, funding opportunities, or potential collaborations, helping researchers make informed decisions.
• – Recommendation systems: By employing machine learning algorithms, Digital Science can provide personalized recommendations to researchers, suggesting relevant articles, journals, or research resources based on their interests and previous activities.
• – Data visualization and exploration: AI-powered tools enable the creation of interactive visualizations and data exploration platforms, allowing scientists to gain deeper insights from complex datasets and facilitate data-driven decision-making.

These are just a few examples of how Digital Science incorporates AI into its offerings. The field of AI is rapidly evolving, and new applications are continually emerging to support scientific research and discovery.”
Source: ChatGPT

While all of the information presented by the AI is correct, it is broken down by technical functionality, only presenting ‘examples’ of how technology is used and not what it is used on. As such, it is technically very accomplished, but of little interest to most audiences who would miss the context of how the technology is actually being applied.

AI vs Humans

In 2023 while all the hoo-haa around Generative AI was at its peak, Digital Science launched a campaign called ‘Mind the Trust Gap’ which sought to underline the importance of trust in research among those who both carry out research itself and the rest of us who depend on its integrity and quality. The developments in AI technology are often compared to humans like it is some sort of competition or even battle, but it is perhaps more sensible to view it as a relationship entering a new phase, and trust is key to that relationship. As long as we can use AI with transparency and openness like the examples above, we can build a better understanding of the world around us.

Can our AI-powered solutions help you?

Talk to us

The post AI at Digital Science appeared first on Digital Science.

Related articles

figshare

Read More

Advancing Openness and Responsibility

Read More

Global Attitudes Towards Open Data

Read More

The post The State of Open Data 2022 appeared first on Digital Science.

Researchers are left to navigate a system that makes it harder than not to share and where, most alarmingly, the public may only fully understand the importance of data sharing when it’s shown to have gone dramatically wrong. There’s no time to lose.

Ginny Barbour | Open Access Australasia

The answers lie in the harmony needed between policies, infrastructure and practices.

Natasha Simons | Australian Research Data Commons (ARDC)

What you’ll find inside:

Related articles

figshare

Read More

Advancing Openness and Responsibility

Read More

Global Attitudes Towards Open Data

Read More

The post The State of Open Data 2021 appeared first on Digital Science.

The post Navigating Networks of Oncology Biomarkers appeared first on Digital Science.