My colleagues and I recently published the paper, Classifying Vaccine Misinformation in Online Social Media Videos using Natural Language Processing and Machine Learning, which was presented at HICSS 57 in Oahu, Hawaii. The paper presents on machine learning approaches to detecting misinformation in social media videos related to vaccines. Below is the tag cloud, abstract and full citation of the research.

Abstract

The spread of information through online social media videos is one of the most popular ways to share and obtain information, while at the same time the spread of misinformation across these same social spaces has become a significant concern affecting human well-being. Being able to detect this misinformation before it spreads is becoming more and more desirable for many social media platforms. This research focuses on exploring the accuracy of detecting misinformation across two social media platforms, YouTube and BitChute. This involves the classification of video data into two types: genuine information or misinformation.  More specifically, this research generates additional metadata embedded within online videos related to the COVID-19 vaccination. Using natural language processing (NLP) we extract medical subject headings (MeSH) terms from video transcripts and classify videos using four machine learning techniques including naïve Bayes, random forest, support vector machine, and logistic regression. Implementation of each classifier is presented, and the accuracy of each technique is compared and discussed. 

Reference

S. Schmidt, B. Thoms, E. Eryilmaz, J. Isaacs, “Classifying Vaccine Misinformation in Online Social Media Videos using Natural Language Processing and Machine Learning,” Proceedings of Hawaiian International Conference on System Sciences (HICSS 57), January 2-6, 2024.

Read More

Recent news has raised the alarm for how internet companies manage user data. The biggest concern, at least according to U.S. lawmakers is TikTock, which has been criticized for its extensive data collection of user data, including personal information, location data, device information, and browsing history. Lawmakers have attempted to prove that foreign Influence and TikTok’s Chinese ownership (by ByteDance) pose a national security threat by the Chinese government. Whether true or not, TikTock is just one company in an ever-growing number of internet companies that exploit user data.

The HTTP Cookie has been around since the heyday of the Dotcom Era and remains the simple, yet core technology that supports how user data is tracked across websites. Specifically, cookies are critical for:

1. Personalization: Websites use cookies to remember your preferences and provide personalized content and experiences.
2. Analytics: Cookies track user behavior on websites, such as pages visited, time spent on each page, and links clicked. This data helps website owners analyze and improve their site’s performance and user experience.
3. Advertising: Third-party cookies are often used by advertisers to track users across different websites and deliver targeted advertisements based on their interests and browsing history.
4. Authentication: Cookies can store login credentials and session information, allowing users to stay logged in to websites and access restricted content without having to re-enter their credentials each time.

Today, internet users are provided with ‘more’ transparency in how websites use these cookies. An interesting article on Wired.com (https://www.wired.com/story/cookie-pop-up-ad-tech-partner-top-websites/) discusses this phenomenon in elaborate detail. In California, for example, websites are required to ask permission to collect and share cookie data with ‘partners’, providing more information to internet users. And we all know that more information is always better, right? Maybe yes, maybe no. Obviously there are many different types of internet users. Some users might prefer to micromanage cookie access, while others might prefer a broader solution where a single policy could apply to a larger swath of websites. In any case, this is a gentle reminder to pay attention to those pop-up notifications, because you are being tracked and the page you land on is just the first stop in a vast network of data sharing ‘partners’.

Read More

Hot off the presses, How to Build a Health eProfile: Empowering Yourself with Personal Health Data, aims to help individuals unlock the power of their personal health information. Through the creation of a comprehensive Health eProfile, individuals can gain valuable insights into their health and make informed decisions about their lifestyle and healthcare choices.

The book is now available for purchase on Amazon and Kindle Stores: https://www.amazon.com/dp/B0CSXHVJBX?ref_=cm_sw_r_cp_ud_dp_GHVV0HRMK0RX5QXE9HPM

In this book, readers will learn:

• How to gather and store health information in a secure and easily accessible location.
• The importance of data quality and how to ensure the accuracy and reliability of health data.
• How to utilize a Health eProfile to make informed decisions about personal health and lifestyle.
• The best practices for sharing a Health eProfile with trusted friends, family, and healthcare providers.
• Essential considerations for building a successful Health eProfile, including privacy and security, data storage, and access.

Read More

Most of us are familiar with Artificial Intelligence, aka, AI. If you are new to the game, check out this Wikipedia link.

Eloquently defined by ChatGPT, AI is a field of computer science and technology that focuses on creating systems and machines capable of performing tasks that typically require human intelligence. These tasks can include understanding natural language, recognizing patterns, solving problems, making decisions, and learning from experience. AI systems aim to simulate human-like cognitive functions and processes, albeit often in a more specialized and narrow context. AI can be categorized into several subfields, including: machine learning, deep learning, natural language processing, computer vision, robotics, expert systems, reinforcement learning, and AI planning. Some systems, like ChatGPT incorporate many of these fields, but what makes ChatGPT so effective is its combination of deep learning, natural language processing (NLP), and neural network architecture, which is built atop a tremendous amount of data across a large distribution of powerful servers.

How we decide to incorporate AI into our daily lives will largely dictate how effective AI can will be. Used in the field of healthcare, AI shows promising potential in drug discovery and treatment plans based on an individual’s unique genetic composition. On the opposite end this spectrum, AI can be used for maleficent purposes, including robotic warfare or social profiling. AI’s impact on humanity can also be more nuanced. Take for example AI’s ability to generate ‘art’ or write music. How society addresses the many challenges of AI remains to be seen, but for the time being, AI is continues to happen all around us, whether we are aware or not. Either way, for now, let’s give Weird Al some love:

Read More

Halloween is one of my favorite days of the year. What other day allows anyone and everyone to dress up in costumes, visit haunted houses and hand out candy. It can be fun for both kids and adults alike. The notion of the spooky holiday dates back over 2,000 years, and is rooted in ancient Celtic festival of Samhain, which marked the end of the harvest season and the beginning of winter. The Celts believed that on the night of October 31st, the boundary between the living and the dead was blurred, and ghosts and spirits could roam freely. While that’s good enough reason to stay in, universal participation in the holiday gives plenty reason to get out and explore the neighborhood.

I grew up in a less technical era, where Halloween decorations consisted of pumpkin carvings, skeletons and spider webs. Today’s digital age offers new ways to scare, making it possible to take your Halloween celebrations to the next level of spookiness and fun. Just take a look at these creepy looking holograms!

Here are some more examples of Halloween-themed technology and tech-related activities:

1. Smart Halloween Decorations: You can use smart lighting systems like Philips Hue or smart plugs to control your Halloween decorations remotely. Set up eerie lighting effects or automate your decorations to turn on and off at specific times.
2. Augmented Reality (AR) and Virtual Reality (VR) Apps: Download Halloween-themed AR apps or games that can transform your surroundings or take you on virtual ghost tours. VR can also be used for immersive horror experiences.
3. Halloween-Themed Apps: There are many apps available for creating digital Halloween decorations, finding nearby haunted houses, or generating spooky soundscapes.
4. 3D Printing: Create your own custom Halloween props and decorations using 3D printing technology. You can find a plethora of designs online, from pumpkin carving stencils to spooky figurines.
5. LED Costumes: Design costumes with LED lights or EL wire to create glowing, eye-catching effects. These costumes can be programmed to change colors and patterns.
6. Online Costume Shopping: Technology makes it easier to shop for Halloween costumes. Many websites and apps offer virtual try-on features, allowing you to see how a costume looks on you before buying.
7. Halloween-Themed Video Games: Play spooky video games to get into the Halloween spirit. Many games release special Halloween events or updates during the season.
8. DIY Electronics Projects: Create your own Halloween-themed electronics projects, such as motion-activated props, sound-activated decorations, or Arduino-controlled displays.
9. Home Automation: Use home automation systems like Amazon Alexa, Google Home, or Apple HomeKit to control Halloween decorations, play spooky music, or trigger Halloween-themed routines with voice commands.
10. Social Media and AR Filters: Platforms like Instagram and Snapchat often introduce special Halloween-themed augmented reality filters and stickers to enhance your photos and videos.
11. Halloween-Themed Soundtracks and Podcasts: Listen to creepy podcasts or Halloween-themed music playlists using streaming services like Spotify or Apple Music.
12. Drone Decorations: Drones equipped with LED lights can create spooky aerial displays in the night sky for your Halloween party.
13. Escape Room Games: Many places offer Halloween-themed escape room experiences that blend technology with interactive storytelling for a spooky adventure.
14. Smart Doorbells: Upgrade to a smart doorbell with a camera, which allows you to see and interact with trick-or-treaters, even when you’re not at home.
15. Virtual Halloween Parties: Host virtual Halloween parties using video conferencing tools and online games to celebrate with friends and family.

Read More