Angelica Lo Duca
(She/Her)
As seen in:
Medium,
Wiley Online Library,
Journal of Marine Science and Engineering,
MDPI,
Communications of the ACM,
Flipboard,
O'Reilly Media,
Smashing Magazine,
Towards Data Science,
KDnuggets
and
Covers:
Data Science, Web Applications, Tech Writing
Articles by Angelica Lo Duca
Journal of the Association for Information Science and Technology | Wiley Online Library
1 INTRODUCTION Information science organizes, processes, and communicates data, information, and knowledge. As information environments become increasingly complex, new technologies, including Generative Artificial Intelligence (AI), offer transformative potential in how insights are extracted, structured, and presented (Gozalo-Brizuela & Garrido-Merchan, 2023).
Leveraging LLMs to Support Semi-Automatic Report Generation
empowerment through data, knowledge, and expertise. Join DDI community at https://join.datadriveninvestor.com Data Reporting, Artificial Intelligence An overview of the work I presented at the CHIRA 2025 conference Press enter or click to view image in full size I recently presented my work at CHIRA 2025, where I shared a project titled MeteoChat A Fine-tuned and RAG-based LLM for Semi-Automatic Report Building in Environmental Monitoring.
Testing Data Stories with Simulated Audiences
A few months ago, I presented a data story about historical data to a room full of historians and experts. They knew the history, the issues, the data. But when I showed them how there was a connection between data in historical archives and real people, something unexpected happened. The room went silent. A few people teared up. It was one of those rare moments when data transcends numbers and becomes emotion. Some months later, I gave the exact same presentation to a group of high school students.
[2511.04024] The Benefits of Data Storytelling in Accessible Teaching
arXiv:2511.04024 (cs) View PDF Subjects: Computers and Society (cs.CY) Cite as: arXiv:2511.04024 [cs.CY] (or arXiv:2511.04024v1 [cs.CY] for this version) https://doi.org/10.48550/arXiv.2511.04024 Journal reference: 2nd Workshop on Teaching Accessibility Across Disciplines (TA2D), 2025 Submission history From: Angelica Lo Duca [ view email] [v1] Thu, 6 Nov 2025 03:46:46 UTC (342 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Connected Papers Toggle Connected...
Why Machine Learning Challenges Still Matter in the Age of Generative AI Original
Data Science, Artificial Intelligence Three years after publishing Comet for Data Science, I’m revisiting the timeless challenges of Machine Learning, now amplified in the age of Generative AI. Press enter or click to view image in full size It’s been three years since I published my first book, Comet for Data Science, and so much has changed. Back then, Machine Learning was the hottest topic in AI. Today, it almost feels like old news.
Conflict, Montage, and AI in Data Storytelling
Data storytelling involves communicating the results of data analysis through a compelling narrative. In a previous post,1 I examined how cinematic techniques, including narrative arcs, character roles, and visual framing, can be applied to data storytelling. That discussion focused on foundational concepts, emphasizing how a three-act narrative structure can help organize insights into a compelling journey anchored in the data itself.
Reimagining Data Literacy for Blind Children with AI and Storytelling
Data Storytelling, AI, and Education Behind the scenes of our ICS Exchange 2025 paper: A personal look at how AI can orchestrate multidisciplinary innovation for inclusive education. A few days ago, I had the pleasure of presenting our research at the ICS Exchange 2025 conference. This project was born from an inspiring collaboration with a team of researchers and professionals, including Marina Buzzi, Barbara Leporini, Veronica Punzo, Daniela Rotelli, and me.
The Narrative Power of Data
We often work with various datasets ranging from healthcare and tourism to finance. As technical experts, we excel at analyzing them, building sophisticated models, and crafting visually appealing dashboards. Yet, one skill we often overlook is communicating these insights to people who don’t share our domain expertise.
Three Books You Should Read to Improve Your AI Knowledge
Books, Artificial Intelligence Three resources to learn more about Retrieval Augmented Generation (RAG), LangChain, and Multi-Agent systems Lately, AI-related concepts such as RAG and multi-agent have been all the rage. Maybe we all know these words a little, but then we don’t fully understand how to implement and use these systems in practice. Personally, I see a lot of posts and links to exciting resources on social media, but they focus on a single aspect at a time.
Introducing PyNarrative: A Python Library for Data Storytelling
Data Storytelling, Python An overview of the new Python library for data storytelling. Data visualization is crucial for understanding complex datasets, but visualizations alone are insufficient to make audiences understand the message in the data. Data storytelling addresses this by integrating narratives with visual elements, making insights more memorable and actionable (Lo Duca, 2025).
The Human Element: Using Research And Psychology To Elevate Data Storytelling — Smashing Magazine
23 min read UX, Design, Storytelling Share on Twitter, LinkedIn Effective data storytelling isn’t a black box. By integrating UX research & psychology, you can craft more impactful and persuasive narratives. Victor Yocco and Angelica Lo Duca outline a five-step framework that provides a roadmap for creating data stories that resonate with audiences on both a cognitive and emotional level.
Two Books You Should Read to Change Your Mindset
Books, Data Analysis A reflection on Chart Spark by Alli Torban, and Making Numbers Count by Chip Heath & Karla Starr. When you choose a book to read, choose it well. Life is too short to read bad books. If a book doesn’t give you anything, leave it alone and pick up another. Maybe that book will be ideal for someone else but not for you. Today I want to suggest two books I read with pleasure and have broadened my horizons.
Four Ways to Credit a Source in a Chart
Data Visualization, Data Storytelling A practical tutorial on where you should place credits in your next data visualization When you build a chart with data that is not ours, you must cite the source from which you took the data. This serves to do justice to the work done by others and increase your credibility towards those who will look at the graph. If you cite the data source, your chart will surely be more authoritative because it is based on verifiable data.
Data Storytelling with Altair and AI
Look inside The Art of Data Storytelling Source code Book forum Source code on GitHub The Art of Data Storytelling Register your pBook for a free eBook more This book 1° 2° 3° access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks! choose one free eBook per month to keep exclusive 50% discount on all purchases access to all Manning books, including MEAPs! 5, 10 or 20 seats+ for your team - ePub + liveBook available Sep 16, 2024 Look inside Great data presentations tell a...
Four Ways to Explain Insights Extracted from Data
Data Analytics, Data Science A tutorial on connections, coincidences, curiosity, and contradictions as strategies to explain insights from data. Explaining why something happens in your data is not easy. You may even find something exceptional in your data, but after your discovery, you must explain why this event occurred. In this article, I’ll show four possible strategies to explain your insights.
Meet the Author of Effective Data Analysis: Mona Khalil
Books, Data Analysis Today I have the pleasure of interviewing Mona Khalil, author of the book Effective Data Analysis by Manning Publications. As always, before getting to the heart of the interview, I'll reveal some behind-the-scenes secrets. Browsing the book catalog on the Manning website (which is always full of new proposals), I found Mona's fascinating book. As soon as I started reading it, I found everything I was looking for about data analysis.
The Future of Finance with ChatGPT and Power BI
Finance, Generative AI Lately, I have seen various guides, books, courses, and more or less detailed articles circulating on the web on how to use Generative Artificial Intelligence and, in particular, ChatGPT to carry out various tasks. I am also working on integrating GenAI into data storytelling. However, I never thought that GenAI could be applied to the finance sector, given that it is a very delicate area requiring a lot of attention.
Effective Data Analysis by Mona Khalil
Books, Data Analysis This book must be read. If you are an aspiring data analyst or are looking for a reference manual, this book absolutely cannot be missing from your shelf. Personally, I didn't think that much of the theory of data analysis could be concentrated in one book. Yet, in the book Effective Data Analysis, Mona Khalil manages to condense and brilliantly describe what it takes to embark on the data analyst's journey.
How to Tailor a Chart to an Audience of Professionals
Data Visualization, Data Storytelling A ready-to-run tutorial showing how to tailor the global temperature anomalies dataset for an audience of professionals, using Python and Altair Did you know that the same dataset can be graphically represented differently based on the audience we have in front of us? This is because each audience has different requirements, meaning that each audience will look for something different in the data.
Book Review: A Damn Fine Stable Diffusion Book by Will Kurt
Books, Generative AI My thoughts after reading the first three chapters of this book by Manning Publications I finally found the time to write an article on the blog…Recently, in fact, I have been busy with various activities that have entirely absorbed me, including completing the revision of my book, which has finally gone into production. Which means it should be released in August. But that’s another story.
Combining Data Management and Data Storytelling to Generate Value
Lately, I have been focusing on data storytelling and its importance in effectively communicating the results of data analysis to generate value. However, my technical background, which is very close to the world of data management and its problems, pushed me to reflect on what data management needs to ensure you can build data-driven stories quickly. I came to a conclusion that is often taken for granted but is always good to keep in mind. You can’t rely only on data to build data-driven stories.
How to Overlap the Lines of a Trendline Year by Year in Tableau
Data Visualization, Tableau A step-by-step tutorial in Tableau to split a trendline year by year I’ve been trying to learn Tableau for a while now. For those who don’t know, Tableau is software (paid, but with a trial or even free version for students and teachers) that allows you to explore and visualize data. At first glance, it is a very complex software, because it allows you to do many things, including creating single more or less complex graphs, dashboards, and stories.
Remote Sensing for Maritime Monitoring and Vessel Identification
1. Maritime Monitoring According to the statistics published by the United Nations Conference on Trade and Development [1], the total fleet worldwide consisted of more than 2.2 × 10 9 deadweight tons in 2023 with about 105,000 vessels against less than 1.5 × 10 9 in 2011 with about 83,000 vessels.
Genealogical Data-Driven Visits of Historical Cemeteries
1. Introduction Cultural sites are invaluable repositories of historical significance, offering information on the heritage and history of societies. However, the passage of time often obscures these sites’ original context and meaning, making it challenging for contemporary visitors to fully comprehend their cultural and historical importance. Over the past twenty years, a great effort has been made to provide cemeteries the status of cultural and touristic sites.
How to Compare a Classification Model to a Baseline Original
Data Science, Machine Learning A ready-to-run tutorial in Python and scikit-learn to evaluate a classification model compared to a baseline model The other day, I had to understand if my classification algorithm's performance was decent. I had obtained a precision, recall, and accuracy of 64%, and I honestly thought I had obtained a terrible result. In fact, 64% was a little better than a random model. In reality, this is true if the problem to be solved is simple.
Three Ways to Calculate the Similarity Between Two Strings Original
textPython, Text Analysis A tutorial in Python using the jellyfish library to calculate the similarity between two strings Lately, I’ve been working on a project for matching surnames. I have a dataset of surnames, some of which potentially contain typos. My goal is to identify which surnames are potentially incorrect and then correct them.
How Generative AI Can Help You Improve Your Data Visualization Charts - KDnuggets
Leaked Google Pixel 9 Pro images don't look like any Pixel you've ever seen Google's Pixel phones are some of the best smartphones on the market, at the very least when it comes to software and photos. However, while the …
How Generative AI Can Help You Improve Your Data Visualization Charts
Image from DALLE 3 5 Key Takeaways: The basic structure of a data visualization chart Using Python Altair to build a data visualization chart Using GitHub Copilot to speed up chart generation Using ChatGPT to generate relevant content for your chart Using DALL-E to add engaging images to your chart Are you tired of spending hours creating boring data visualization charts? Use the power of generative AI to improve your data visualization.
Meet the Author of Design for the Mind: Victor Yocco
Meet the Author of Design for the Mind: Victor Yocco Today’s special guest is Victor Yocco, author of the book Design For the Mind published by Manning Publications. Before going to the heart of the interview, I would like to tell you, as usual, some background.
How to Tailor A Column Chart for Communication
A practical example showing the simplification process in Python Altair Drawing a column chart helps represent categories and values. However, a column chart is sometimes too overwhelming with useless content, and the audience may struggle to understand what it means.
Meet the Author: The Complete Obsolete Guide to Generative AI
Meet the Author: The Complete Obsolete Guide to Generative AI Today's special guest is David Clinton, the author of The Complete Obsolete Guide to Generative AI, published by Manning Publications. Before we get into the details of the interview, I would like to share some background with you. After preparing the questions, I sent a LinkedIn message to David, who kindly said he would answer the questions the following day. And so it was. No sooner said than done.
Scientific Focus on the Paper: Why is AI not a Panacea for Data Workers?
Scientific Focus on the Paper: Why is AI not a Panacea for Data Workers? Data storytelling is challenging and time-consuming since it involves various steps, such as data collection, analysis, visualization, narration, and presentation. Therefore, it is natural to wonder if and how AI can assist data workers in this task and the benefits and drawbacks of human-AI collaboration in data storytelling.
Book Review: The Complete Obsolete Guide to Generative AI
David Clinton won me over for his writing style, which was never overly ironic or humorous, and for the book's content. The Complete Obsolete Guide to Generative AI is a comprehensive resource guiding the reading throughout the journey of Generative AI.
A Year of Books: Which Ones I’ve Read and Suggestions for 2024
A Year of Books: Which Ones I’ve Read and Suggestions for 2024 2023 is coming to an end, and it’s time to take stock, even in the field of reading. Aside from the countless books I read to my children about talking animals and adventures of various kinds, this year has been a good year for reading. I have read four books from the beginning to the end, which is a great honor, considering that the time for personal reading has been reduced to practically zero in recent years.
Definitions: Zero-shot Prompting vs. Few-short Prompting
For those getting started with prompt engineering in large language models (LLMs), the following definitions may help. Zero-shot Prompting is when you use an LLM, as it is, in a domain different from the one in which it was trained. This type of prompting assumes that the overall knowledge of an LLM may also cover a specific domain. Few-short Prompting is when you fine-tune an LLM with a limited number of labeled data. Usually, you use this technique when the labeled data is scarce.
Using Vega-Lite for Data Visualization
A tutorial on how to start using Vega-Lite to draw charts. Vega-lite is a concise JSON representation of a Vega visualization. Vega is a visualization grammar used to represent the elements of a data visualization chart. For those who know D3.js, you can imagine the output produced by D3.js as very close to that produced by Vega. For those who are not familiar with D3.js, you can think of Vega as a description in JSON of your chart, including axes, scales, types of marks, and so on.
Book Review: Design for the Mind by Victor Yocco
Book Review: Design for the Mind by Victor Yocco I have always been fascinated by psychology, but my IT background (and also a bit humanistic, to tell the truth) has always limited me in understanding this study area. Yet, when working in the data…
How to Improve Your ChatGPT Outputs Using Configuration Parameters
ChatGPT, Generative AI A focus on configuring the temperature, the Top P, the frequency penalty, and the presence penalty directly in your ChatGPT prompts I’ve recently been reading a very interesting book by David Clinton, entitled The Complete Obsolete Guide to Generative AI, published by Manning Publications. In the second chapter, the author describes what the main parameters of an AI model are and how to configure them to adapt to their needs.
Using Slope Charts to Simplify Your Data Visualization
Data Visualization, Data Storytelling Simplify your overwhelmed charts by using slope charts: a tutorial in Python Altair We may plot charts to include as many concepts as possible in our visualization. As a result, our chart could be difficult to read and distracting. For this reason, before plotting anything, sit in your chair and plan what you want to communicate. Then, look at your data and decide what is effectively necessary to plot. Leave the rest out of your visualization.
Generative AI for Data Analytics
Generative AI, Books Introduction to the use of Generative AI in Data Analytics Using Generative AI to ensure sufficient Data Quality Descriptive analysis and statistical inference supported by Generative AI Utilizing Generative AI for result interpretation and formulating recommendations Basic Text Mining using Generative AI Advanced Text Mining with Generative AI Scaling and Performance Optimization Risk, Mitigation, and Trade-offs Over the last year, we have been assisted in developing...
Towards a Framework for AI-Assisted Data Storytelling
Data Storytelling, Generative AI An overview of the paper I presented at the 19th International Conference on Web Information Systems and Technologies (WEBIST 2023) Lately, generative AI (GenAI), a subfield of artificial intelligence aiming to generate new content from what has been learned, has increasingly gained ground. Since one of my research areas is data storytelling, I wondered if GenAI and data storytelling could work well together.
Mastering Batch Data Processing with Versatile Data Kit (VDK)
Data Management A tutorial on how to use VDK to perform batch data processing Versatile Data Kit (VDK) is an open-source data ingestion and processing framework designed to simplify data management complexities. While VDK can handle various data integration tasks, including real-time streaming, this article will focus on how to use it in batch data processing.
Mastering Batch Data Processing with Versatile Data Kit (VDK)
import inspect import logging import os import pandas as pd import requests from vdk.api.job_input import IJobInput def run(job_input: IJobInput): """ Download datasets required by the scenario and put them in the data lake.
Monitoring Spark NLP Pipelines in Comet
Just recently Comet reached another milestone with its integration with Spark NLP. Now you can monitor your NLP experiments directly inside of Comet. Thanks to this integration, you can monitor your NLP pipeline directly in Comet, either during the training process or when it finishes. Spark NLP is a library for Natural Language Processing released by John Snow Labs. It is 100% open source and supports different programming languages, including Python, Java and Scala.
Hyperparameter Tuning in Comet
Hyperparameter tuning is one of the most important tasks in a Data Science project lifecycle because it determines the performance of our Machine Learning model. Many tools and strategies can be used to perform hyperparameter tuning, including (but not limited to) the following well-known Python libraries: Tree-based Pipeline Optimization Tool (TPOT) Hyperopt-Sklearn Auto-Sklearn In this article, I focus on the Comet Optimizer, provided by Comet.
Three Charts to Represent a Percentage You May Not Know Original
Data Visualization, Python A ready-to-run tutorial in Python Altair to build charts to represent a percentage Representing a percentage visually may engage the audience more and help them better understand the data. There are different ways to represent a percentage visually. The most straightforward strategy is a Big Number (BAN), as shown in the figure below. In addition to BAN, there are other ways to represent a percentage visually.
How to Use ChatGPT to Convert Text into a PowerPoint Presentation
Photo by ThisisEngineering RAEng on Unsplash Are you tired of spending hours creating PowerPoint presentations from lengthy texts? Do you wish there was a faster way to convert your content into engaging slides? Use ChatGPT to transform your text into a presentation in just minutes.
How to Use ChatGPT to Convert Text into a PowerPoint Presentation
19 hours ago Anthropic’s chatbot can analyze up to 75,000 words at a time, and lets you attach multiple files and direct the bot on aspects you want to analyze. Claude has surprising capabilities, including a couple you won’t find in the free version of ChatGPT. Since this AI bot launched on July 11, I’ve found …
Learning and Operating Presto
The Presto community has mushroomed since its origins at Facebook in 2012. But ramping up this distributed SQL query engine can be challenging even for the most experienced engineers. This practical book shows you how to begin Presto operations at your organization to derive insights on datasets wherever they reside. Authors Angelica Lo Duca, Vivek Bharathan, and George Wang explain what Presto is, where it came from, and how it differs from other data warehousing solutions.
The AI-Powered Developer by Nathan B. Crocker
Generative AI, Books In the generative AI era, updating yourself on tools such as ChatGPT, GitHub Copilot, and Amazon CodeWhisperer is almost mandatory. In the book The AI-Powered Developer, published by Manning and currently in MEAP, Nathan B. Crocker guides the reader in using ChatGPT, GitHub Copilot, and Amazon CodeWhisperer as programming assistants.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Angelica
Contact Angelica, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack