How to Find Photos and Images in Old Newspapers with Newspaper Navigator

Elevenses with Lisa Episode 26 Video and Show Notes

Live show air date: September 24, 2020
Join me for Elevenses with Lisa, the online video series where we take a break, visit and learn about genealogy and family history.

Newspaper Navigator is a new free online tool for finding images and photos in old newspapers at Chronicling America. It doesn’t work the way the Library of Congress website works, so in this episode I show you how to navigate the Newspaper Navigator. It’s a fun session that will have you finding new newspaper gems in no time!

About LOC Chronicling America

Chronicling America is sponsored jointly by the National Endowment for the Humanities and the Library of Congress. It features free digitized historic newspapers spanning 1789-1963.

Newspapers Contain Imagery such as:

  • Photos
  • Drawings
  • Maps
  • Cartoons
  • Advertisements

You may not find the newspaper that you need for your research in the Chronicling America digitized collection. In those cases, turn to the US Newspaper Directory. It catalogs newspapers published 1690-present. Click the US Newspaper Directory button on the Chronicling America website to search. The catalog will tell you where known copies of the paper can be accessed.

Uses of Newspaper Images

Most of the old newspapers featured in Chronicling America include images. And because these old images are in the public domain, they are an ideal complement to family histories.

If you are very fortunate you may find photos or images of your ancestors, their homes, or other things specifically about your family.

Newspaper images are also a wonderful source when you need a photo or image to represent an important idea or item when telling your family’s story, whether in a blog post, article, book, video, PowerPoint presentation or other medium. Example of this would include a photograph of a blacksmith shop in the 1890s in the area where your ancestor worked as a blacksmith, or an advertisement for a Sears home kit just like the one your grandfather built.

Chronicling America’s Newspaper Navigator

The Newspaper Navigator dataset currently consists of 1.5 million pieces of extracted visual content from 16,358,041 historic newspaper pages in Chronicling America.

The visual content was identified using an object detection model trained on annotations of World War 1-era Chronicling America pages, made by staff and volunteers.

This “visual content recognition model” detects the following types of content:

  1.  Photograph
  2.  Illustration
  3.  Map
  4.  Comics/Cartoon
  5.  Editorial Cartoon
  6.  Headline
  7.  Advertisement

It also includes text corresponding to the imagery, identified by Optical Character Recognition (OCR).

Searching the Newspaper Navigator

You can search all images with captions. The results will be returned in a Gallery view featuring up to 100 images per page. This results format makes it very easy to quicky browse the images.

You can also switch to List view which lists the images along with the text retrieved by OCR.

How to Find Images Faster in Old Newspapers

Run a search in Newspaper Navigator of the word baseball and then run the same search in Chronicling America. A comparison of the results highlights the between Chronicling America and Newspaper Navigator when it comes to finding images in old newspapers.

Word Searched: baseball
Results returned:
Newspaper Navigator: 5,427
Chronicling America: 921,534

The search results returned by the Newspaper Navigator are solely focused on photos and images. This means you have a fraction of the number results to review. Another big advantage of Newspaper Navigator over Chronicling America is the size of the image. Newspaper Navigator gives you just the large image to review, while Chronicling America shows you a thumbnail of the entire page with images so small that you must click and load the page to analyze them.

finding photos in newspapers at Chronicling America

Images appear much smaller at Chronicling America and require you to click through to the page for closer examination.

Start by running a keyword search. (example: Blacksmith). On the results you can filter the results by Location and Years. Because the search currently doesn’t support Boolean operators or other types of search operators, you may need to run a few different versions of the same search to get a complete picture of the potential results. We’ll talk more about search strategies in just a moment.

Once you find an image you want, click to open it. The pop-up box offers these four buttons:

  • Download Image – Downloads a high-resolution copy to your hard drive.
  • Cite this – Generates a source citation that is automatically copied to your computer clipboard. Then you can simply paste it as needed. You can also cite the dataset by including the image URL, plus a citation to the website such as “from the Library of Congress, Newspaper Navigatordataset: Extracted Visual Content from Chronicling America.” According to the website, all images are in the public domain and free to use. Learn more about Rights and Reproductions at https://chroniclingamerica.loc.gov/about/.
  • Learn about this newspaper – Takes you to the Chronicling America catalog listing for the newspaper from which the image comes.
  • View Full Issue – Takes you to the complete newspaper issue at the Chronicling America website.
Newspaper image option buttons

Click the buttons to select the options

My Collection at Newspaper Navigator

You can gather and save collections of the newspaper images you find using Newspaper Navigator. Start by running a search. On the results page click to select the desired images, then click the Save button. This will generate a URL for that collection and copy it to your clipboard. Since Newspaper Navigator doesn’t currently allow you to log in and return to your past searches during different sessions, I suggest pasting the URL into a research log for future reference.

Train My AI Navigators at Newspaper Navigator

A unique feature of the Chronicling America Newspaper Navigator is the ability to “train” the site to search for you. It does this through machine learning.

Train My AI Navigator

Elevenses with Lisa Episode 26

How to Train My AI Navigator:

  1. Run a search
  2. Click to select desired images
  3. Click Save to save the collection of images
  4. Click Train My AI Navigators
  5. Newspaper Navigator will deliver a new set of images based on your selected images. On that page, select additional images that you want by clicking toward the top (+) of the image.
  6. Click unwanted images by clicking toward the bottom (-) of the image.
    selecting unwanted images from historic newspapersClick to select the images you don’t want the AI Newspaper Navigator to find.
  7. Click Train My AI Navigator again
  8. Continue adding and subtracting images as needed to further train the system
  9. Type a name for this training session in the Name My AI Navigator The saved AI Navigator name will appear in the Select an AI Navigator column
  10. Click Save to generate a URL for this training session and paste into your research log.
  11. Click + New AI Navigator to create a new training session spring boarding from the first
  12. Click Clear & Restart to start a new search

Newspaper Navigator Search Strategies

Newspaper Navigator doesn’t, as of this writing, support Boolean Operators or offer an advanced search field. Here are some strategies that can help you have more success in searching the site:

Don’t use search operators, use variations

Even a space between initials can make a difference.

Variations in newspaper searches

Each variation has the potential to deliver a different result in newspaper images.

Search Locations

Considering how many variations there can be to a name, when searching for ancestors try searching first on the name of their town or location. If there are still quite a few results, you can then filter to only newspapers from their state. I search the town name first because an article may appear in a newspaper from a different state. In the case of my search for McMinnville, I received a small, manageable results list. Had it been large and included both McMinnville, TN and McMinnville, OR, filtering to just Oregon would be helpful.

Test your search theories

Analyze your results and try variations based on what you are learning about what Newspaper Navigator is focusing on.

Search for word strings

In testing my search theories, I learned that Newspaper Navigator did not do well with multiple words that do not appear right next to each other. Therefore, I tried to find word strings that pertained to my family that I could search for such as the name of a business: Consolidation Coal Company.

Search for Photos

Another interesting search you can run is the word Photo. On the results page filter to the state and years that apply to your research.

Use List View to Find on Page

When dealing with a large number of results, List View can help speed up the review process. List View also displays the text generated by OCR. While not perfect, it can be helpful. Use your computer’s Find on Page feature (control + F on a PC, Command + F on Mac) and type in a keyword such as a surname. This will take you instantly to all occurrences of that word in the text on the page. Click the next page and run it again.

Use Control + F to find OCR text in the results list at Newspaper Navigator

Find images quickly by word search in the List View

Learn More About Machine Learning

In the menu click Data Archaeology to learn more about machine learning and the Newspaper Navigator project.

Resources

How to Find Your Family History in NewspapersPremium Video & Handout: Getting the Scoop from Old Newspapers. (Not a Premium member yet? Learn more here.)
Book: How to Find Your Family History in Newspapers
Bonus Download exclusively for Premium Members: Download the show notes handout

Please Support this Free Show

If you’re enjoying the show, you can help others benefit from it too by leaving a comment below. Your comments…

  • helps me understand what matters to you.
  • helps others gather new ideas and encourages them to give the show a try.
  • tells Google / YouTube that this show is interesting and worth sending other people to through the search results.
  • provides great potential content for future episodes.

Clicking the red subscribe on our Genealogy Gems YouTube and then giving this video a thumbs up below the videosubscribe to our YouTube channel

By leaving a comment (what you enjoyed, questions you have or what you’d like to see in the future) below this video after the show’s over or at the bottom of the show notes page if you’re watching on my Genealogy Gems website.

 

Answers to Your Live Chat Questions

One of the advantages of tuning into the live broadcast of each Elevenses with Lisa show is participating in the Live Chat and asking your questions. 

Bert asks: Are some newspapers only available for a fee on websites such as Ancestry
Lisa’s Answer: Yes, several genealogy websites have exclusive collections of digitized old newspapers. You can usually search or browse the site for free to determine if they have newspapers from the location and time frame that you need before you make a purchase. Here are some of my favorites that I’ve had good success with:

Genealogy Bank
MyHeritage
Ancestry
British Newspaper Archive (a goldmine for anyone with British ancestors!) 

We are compensated if you make a purchase after using our links above (at no additional cost to you.) Thank you for supporting this free show by doing so!

Christine asks: (What is the ) newspaper navigator date range? 
Lisa’s answer: Here’s a break down of the dates:

Chronicling America covers 1789 – 1963 (digitized newspapers)
Newspaper Navigator covers 1900 – 1963 (photos in digitized newspapers)
U.S. Newspaper Directory at Chronicling America covers 1690 – present (catalog, only some are digitized and those are part of Chronicling America.)

Rachel asks: I have an ancestor that was in the social pages all the time in our local newspaper in the 1800’s. I thought it would make a great book or video, any ideas on how to showcase them the best?
Lisa’s answer: I love both of those ideas and I cover many more in my Premium Membership video Inspiring Ways to Captivate the Non-Genealogists in Your Life. Personally I have found that short photo books and short videos that tell one story are received the best by family members. They both offer opportunities to share and highlight items from newspapers. Learn more about quickly and easily making family history videos by watching Elevenses with Lisa episode 16. And I strongly encourage Premium Members to watch these two videos:

Video Magic: Creating Brilliant Videos Quickly & Easily with Lisa Louise Cooke (creating videos)
Share Your Own Life Stories More Meaningfully with Sunny Morton. (writing books)

lagomcurt asks: ​Are local small-town papers included in the collection?
Lisa’s answer: Yes.  

June asks: ​When you download it ask what to save as. What is your suggestion?
Lisa’s answer: I think you’ll find that JPEG is currently the only option in the Save as Type drop-down menu.

Sharon asks: ​Does Chronicling America have foreign language newspapers in America?
Lisa’s answer: Absolutely! Searching in the language will help retrieve items. 

Ohio Waisenfreund newspaper at Chronicling America

Ohio Waisenfreund newspaper at Chronicling America

Pat asks: ​Does it have Irish American newspapers?
Lisa’s answer:  Chronicling America does have Irish American newspapers. If they were published between 1900-1963 then they will be searchable by Newspaper Navigator. I would also recommend searching all newspapers (online and offline) by clicking the U.S. Newspaper Director button at Chronicling America. Then search by ethnicity (Irish) and Material Type (online.) You will find that some are linked to other websites where they can be found online. If you see an image of a newspaper on the catalog page, then you know it is available on Chronicling America in a digital format. 

how to search for irish newspapers online at US Newspaper Directory

Search for Irish newspapers online at US Newspaper Directory

 

 

Mark asks: Can the wash out pictures be enhance with the new MyHeritage Photo with the sharping feature and colorization to make it a better final experience with images?
Lisa’s answer: Yes indeed. Because the original quality will be poor and with low dots per inch (dpi) it likely won’t improve the way an original photo would. However enhancing and coloring just takes a few seconds and definitely improves the image. Even better, it often makes the print much more readable. I use it on documents too. Click here to try MyHeritage.

newspaper photo enhanced and colorized with Myheritage

Newspaper photo enhanced and colorized with MyHeritage

 

Kathy asks: ​If you do a search in English, will it find the search term(s) in newspapers that were written in German?
Lisa’s answer: No. You will need to search in German to pick up on any German text. However, if the image itself is similar, My AI Navigator should pick it up.

Lucinda asks: Who is in your necklace and the photo behind you, Lisa?
Lisa’s Answer: It’s my maternal grandmother’s high school graduation photo. 

Please Leave a Comment or Question Below

I really want to hear from you. Did you enjoy this episode? Do you have a question? Please leave it below.  You can also call and leave a voice mail at (925) 272-4021 and I just may answer it on the show!

 

Solutions for Broken Website Links

Every genealogist has experienced the frustration of clicking on a link and discovering that the page is gone or the resource is now defunct. Things change rapidly as technology evolves, so it’s a problem that isn’t going away any time soon.

Genealogy Gems Podcast listeners often ask what to do when they run across a broken or defunct website in the show notes of older episodes of The Genealogy Gems Podcast. I’ve got answers for you today that can help you get back on track whenever this happens to you. 

broken genealogy website links solutions

I received this email from a listener of the free Genealogy Gems Podcast, and it’s one I’ve received from lots of listeners and genealogists alike:

“As one of your podcast listeners who is working my way through past episodes, I am running into a bit of frustration that I am wondering if you, on someone else reading this, can help me on. I have tried to get to a couple of websites that guests of yours mentioned, with no success. (I’m listening to episodes from) 2010, where I am at now, (and that) may not be all that long ago for many, but it is an eon in internet terms.

Are you, or anybody else reading this, aware of any person or site tracking genealogy related websites that records/posts notations of name changes, buy-outs by other service providers, or just plain disappearances? You might have mentioned some in the interim, but I’m still a hundred episodes in arrears.”

That’s the wonderful thing about podcasts, you can listen when the episode is published or even a decade later. That’s because podcasts, unlike radio shows, are recordings that you can access whenever it’s convenient for you. But my listener is correct, things change quickly online, and that includes website links I refer to in the show notes web pages of older episodes.

How to Find Information When a Website has Disappeared

I love hearing that listeners are enjoying the free Genealogy Gems Podcast archive. We hear over and over that our listeners pick up something new each time they listen. However, I completely understand the frustration of encountering defunct websites and resources. What a bother they are!

Unfortunately with the speed at which online information changes, it’s just about as impossible to keep years of web content current (while still producing new content) as it is finding a genealogy record that burned in a courthouse fire!

The good news is that with a little persistence, you can probably locate where a source has moved to or find alternatives that may provide the same function. Paying attention to clues and details around the original source itself can lead you to alternatives that can accomplish the same goals or provide the same or similar information. And of course, tracking down information that’s gone missing is certainly a valuable skill in all areas of genealogy!

Here are a few great strategies to help you find information when a website has disappeared:

1. The Wayback Machine Can Find Defunct Sites

1) If you run across a link to a now defunct site, copy the website link. Next, go to the Internet Archive at https://web.archive.org and paste the web address that you copied into the Wayback Machine search field. Press enter on your keyboard to run the search on that address. You may very likely be able to retrieve a screenshot of the page.

Internet Archive Wayback Machine

If you’ve been researching your family history for several years, you’ll probably recognize the screenshot of World Vital Records (below) at the Wayback Machine.

wayback-machine-result

You may not gain access to everything that was there originally, but you’ll very likely glean clues that you can use to find the information you seek on another website using a Google search.

One of the features most recently added to the Wayback Machine is the Save Page Now tool. This helps you capture web pages and add them to the Wayback Machine at the time that you find them. That way, even if the site goes away, you’ll have a copy of the web page for future reference.

This tool works on any web page that allows “crawlers”, which most sites do. Crawlers are used by sites like Google and the Wayback Machine to index information and capture the pages. 

save this page Wayback Machine

To save a web page using the Wayback Machine, copy the web page’s address and paste it into the Save Page Now field. It will bring up the page in your browser and show you that it’s being processed and will be added to the Wayback Machine.

The page will be conveniently stamped with the date that it was captured. This is helpful because even though websites may stay online for years to come, the content on their pages may be changed over time. By using the Save Page Now feature and adding the web page to the Wayback Machine, you will be able to revisit the information that was on that page on that specific date well into the future, regardless of changes that may be made to it over time.

2. Google Your Question

You’ve heard me say it many times: Just Google it! And that certainly applies here. Google is great at finding alternative sources for the same information. No question is a dumb question when it comes to Google. 

If you are running into a challenge with a defunct site or have a question, chances are someone else has had the same question! It may have been posted on a message forum, a blog post or the help section of a website. Google can help you find the question and the answers that were provided. 

Let’s say you come across a link to the World Vital Records website in the syllabus of a class you took several years ago. (If you’ve been researching your family history for a while, then you probably remember this genealogy records website.) And imagine that when you type the link into your web browser, you discover that the link is broken and the website no longer exists.   

Here’s an example of what you could ask Google in order to find out what has happened to the World Vital Records website:

  • When did world vital records close?
  • Sunset notice for World Vital Records  
  • Who acquired World Vital Records?

world vital records search

As you can see in the example search in the image above, the sunset notice for World Vital Records, which was acquired by MyHeritage, was issued in September of 2018. Click the link to the article to read up on all the details. 

When faced with a broken link your first impulse may be to ask another person or someone you see as an expert on the subject. That can work too, but chances are they may just ask you “did you Google it?” That’s because, like it or not, Googling at the moment you have the question is much faster and provides you with the latest information.

Think of Google as asking your question to every single web page in the world – all at once. If the answer is out there, Google can probably find it.

3. Google the Content 

As I said, the internet is growing and changing every day and it is very possible you may find the content is now available elsewhere.

Any good source that provides website URLs will usually include information about what you’ll find on that website. You can use that information to run a Google search. Your goal is to determine if the information you seek is available elsewhere from the same provider, or identify another website that references the same content.

Start by copying short phrases of key information and pasting it into the Google search box. Put quotation marks around the text. Quotation marks are a standard Google search operator and they will tell Google to search for web pages that include that exact phrase, sentence or paragraph. (Quotation marks also work on individual words such as surnames.) If you don’t get an exact search result, remove the quotation marks and place them just around the most important individual key words.

Here’s an example of how this works:

In Genealogy Gems Podcast episode 62 (published back in 2009) I talked with actor Darby Hinton about a new history-themed television series he was producing called Hintons Living History. The show notes include a link to the website devoted to the show. Clicking that link leads to an error page because the website has since been taken down. (For website publishers like myself, we are often faced with the decision between creating new content, or constantly combing through old published content to fix what is out of date. I think you will agree that continuing to create new content is preferable.)

Since the link no longer works, a Google search of the name of the television show in quotation marks (“Hintons Living History”) provides a plethora of information and videos to learn more about the show.

Obvious, But Not Always 

While the solutions I’ve shared here may seem somewhat obvious, time and time again I’ve watched people get befuddled by running into broken genealogy website links. It’s totally understandable. In the excitement of the moment of finding something interesting, getting stopped in your tracks by a broken links creates frustration. Our brains tend to focus on that obstacle and frustration rather than the simple solutions that are available.

Now you have a game plan that you can use so that broken links will only be a blip on your genealogical research path.

This article was originally written in January 2019, and extensively updated August 6, 2019. Can you find the old version on the Wayback Machine?

Lisa Louise CookeAbout the Author: Lisa Louise Cooke

Lisa is the Producer and Host of the Genealogy Gems Podcast, an online genealogy audio show and app. She is the author of the books The Genealogist’s Google ToolboxMobile GenealogyHow to Find Your Family History in Newspapers, and the Google Earth for Genealogy video series, an international keynote speaker, and columnist for Family Tree Magazine.

SHOCKING RESULTS! Should you use AI Chatbots for Genealogy?

Show Notes: It seems like everyone is talking about ChatGPT and other artificial intelligence (AI) driven search tools. Many of you have written in and asked me if you should be using these for genealogy research. In today’s new video, we’ll tackle questions like:

  • What are AI chatbots?
  • What are the top chatbots?
  • Are they private?
  • Why are they free and will they stay free?
  • Should you trust the results?

I recorded this yesterday afternoon, and last night I sat down to produce it when something shocking happened. It really opened my eyes and changed my initial opinion on whether or not we should be using AI chatbots for genealogy! Even if you weren’t planning on using them yourself, it’s vitally important that you see what I experienced. Other people are going to use this technology. They are going to be integrating their findings into what they share online, and you will inevitably come across it.

Watch the Video

Show Notes

Downloadable ad-free Show Notes handout for Premium Members

We’ve talked about artificial intelligence here at Genealogy Gems. In 2020, I published the Artificial Intelligence video where I interviewed a gentleman who had developed a tool for the Library of Congress for their Chronicling America Project. In fact, we did that in another video called Newspaper Navigator. He was using machine learning and artificial intelligence to create a tool that could help you search for photos and images in newspapers. This was something we weren’t doing before. We were limited to text or keyword searches. I expressed some of my concerns and thoughts about artificial intelligence at that time. We also produced a video about the MyHeritage AI Time Machine tool. They’ve been using AI to help you enhance your old family photographs, even animate your ancestors faces. It’s amazing!

Now, the big viral craze is ChatGPT. It’s using a technology that you can find at Open AI. They’re using this technology in an interactive chatbot of sorts. Users enter questions and requests trying to see what ChatGPT would do. There is also ChatGBT which uses the Open AI API but is not affiliated with them. Both are chatbots. 

Top Popular AI Chatbots

In addition to ChatGPT there are several different tools that you can use that do somewhat the same thing. I think the most popular ones are:

They’re a little bit different, and yet the same in many ways. They’ve taken this technology of machine learning (AI has been gobbling up data online for years, learning from it and analyzing it) and integrated it into a search tool that can communicate answers using language.

Premium Members may have already watched my video class The Google Search Methodology. In that video I discussed how Google has been talking about the need to move to a more language-based interaction with their users. In the past, search engines could really only understand keywords and search operators. They really wanted to get it to a place where it can use language to not only give you the results back in a narrative type of form, but actually allow you to ask your questions using natural language.

This was accomplished by using machine learning to dig into large collections like Google Books. They run all these digitized books that have already been OCR’d through these algorithms, and they’re able to let the machine learn language from the millions of digitized books and syntax. And it did. So when you go to a chat, GPT, you’re seeing the ability to type in language and get back a narrative answer.

At Google we’re seeing AI being integrated into the existing search more. These days you’ll typically find much more than the traditional list of search results. We’re seeing “Answer boxes” and “Related Topics” and other drop-down boxes. Bing has been incorporating this as well. However, the AI chat tools are currently separate from standard search.

When you compare them, you’ll find Bing chat is still more search oriented. It doesn’t do as much as far as giving you creative answers. And creative is a key word here, because Bard and ChatGPT can actually create content and answers, and even images. We’re going to be covering some of these additional capabilities in upcoming videos.

Are AI Chatbots Private?

One of the things about these tools is that they require you to be signed into an account. ChatGPT requires that you sign up for a free account. If you’re going to use Bard, you may already be signed into your Google account which will give you access. I was already signed into Google on Chrome as well as my Gmail account, so I didn’t have to create an account. And as soon as I used Bard, I got an email saying, “welcome to Bard”. Bing Chat currently requires that you use Microsoft’s Edge browser. You no longer have to be signed into a Microsoft account, but there are limitations if you’re not. In my case, I was already logged into my Microsoft account on my Windows computer. I’m sure Edge “talks” to my computer, I’m sure Edge “talks” to Chat. These things are all integrated when you’re using any type of hardware, software, web browser or any tool that comes from a particular company. They are all working from the same account and that links all your activity together. That means they’re tracking you.

Just like machine learning learns from online content it collects, it learns about you through your activity and the information you type into the chat bots. It is being recorded and stored. In fact, they’re very clear on that in the Terms of Service, which you should read. It’s much like back in the day when DNA first came out. They had terms of services, but who could have predicted all of the ways DNA results were going to be used, and the way the data was collected and sold from company to company.

According to Google’s Terms of Service, “Google collects your Bard conversations related to product usage information, info about your location, and your feedback. Google uses this data consistent with our Privacy Policy to provide, improve and develop Google products and services and machine learning technologies, including Google’s enterprise products, such as Google Cloud.

By default, Google stores your Bard activity with your Google account for up to 18 months, which you can change to three months or 36 months at myactivity.google.com/product/bard. Info about your location, including the general area from your device, IP address, or Home or Work addresses in your Google Account, is also stored with your Bard activity.”

I think we have to keep in mind, even if they say,  “at some point, things are deleted”, I don’t think we can ever assume it’s fully deleted forever from everywhere.

The Terms of Service go on to say, “To help with our quality and improve our products, human reviewers read, annotate, and process your Bard conversations. Please do not include information that can be used to identify you or others in your Bard conversations.”

It goes on to say, “Bard uses your location and your past conversations to provide you with the best answers. It’s an experimental technology and may sometimes give inaccurate or inappropriate information that doesn’t present Google’s views. Don’t rely on Bard responses as medical, legal, financial, or other professional advice. Don’t include confidential or sensitive information in your Bard conversations. Your feedback will help make Bard better.” So, you’re really helping them develop a new tool when you use it.

ChatGPT currently states that it’s free for now. Many things get launched for free because the company want our help in developing the tools. In the end, we may have to pay to use it.

Basically, the answer to the question, “is it private?” is “No.” When you are logged into an account, nothing is private. It’s being tracked. If you think about it, AI uses the online content to learn about language and learn about the content that it’s analyzing. Well, just consider that this is learning about you. It’s creating a profile of you. Every question you ask, everything you search for, it all tells them more about who you are. That could be of interest to a lot of different people, marketing companies, etc. So, it’s not private, in my opinion.

Why is It Free?

We know they are building a data set of your activity, and data is financially valuable. Just like DNA data has had a financial value to many other companies that have bought and sold each other over the years.

Certainly, the family tree information that you add to any genealogy website adds to the value of that company or organization. Your research is work they didn’t have to do themselves. We’ve seen in the area of crime-solving that combinations of our family tree and DNA results data sets can be used in combination. So, it’s free, because you’re helping them build the tools. And you’re also developing datasets which have value. Social media activity is much the same. Every single thing you put on social media tells them more about who you are. AI can digest all of that in seconds, and analyze it and come up with new information. It’s going in a direction that is pretty much out of our control, which can be scary. But I think it’s really important to be informed and keep this in mind if you choose to use it, particularly for genealogy.

Should you Trust the Information Provided?

Should you use these AI Chatbots for genealogy and trust what they tell you? Here’s what I’ve learned using Bard.

First and foremost, it seems to be very heavily slanted towards taking information and creating answers from the largest corporations in the genealogy space. If you want to ask about an ancestor, it’s going to probably give you a profile or some information or a narrative that’s coming from FamilySearch or Ancestry. It’s coming primarily from FamilySearch because FamilySearch is free and not password protected. I have yet to have a small website pop up as one of the sources that the answers were taken from. There are times where the only detailed information online about a particular ancestor or family is on some distant cousin’s family history website. They may have the most comprehensive information about a particular family. Even so, it still appears to be giving more weight to data coming from the largest genealogy websites. Well, if that’s the case, you’re already there as part of your research. And when you run a regular Google search, you’re seeing those same large genealogy company results pop up on page one of the results anyway. So, it’s not really a lot different from regular search. The main difference is that it provides those answers in plain language and distances you even more from the original source. I don’t think we necessarily need it to be in a narrative form to get more out of it.

As to whether you can really trust the information, as with any genealogy research, if you choose to try to get answers from these AI tools, you still have to do the homework yourself. Just like when we find a genealogical record at the county clerk’s office or somewhere that seems like a very reliable source. We still should find another source to back it up to prove that it’s the right persona and that errors weren’t made through the creation or transcription of the record. Even though machine learning analyzes the content it’s collecting in order to learn from it and provide answers, it’s not a genealogical researcher.

Let’s say that, again, it’s not a researcher.

Genealogy researchers have different skill sets. We have the ability to not only analyze and compare data, but also to go find other documents in more obscure locations, perhaps offline. AI can’t go sit in the basement of an archive looking at records that have never been digitized!

It’s going to be tempting to take what you find at face value. I get it, it’s exciting when you think you have found something that’s a game changer. For example, I was watching an interesting video on YouTube. A young gal was talking about how she was trying to see if she could learn about her ancestors’ lives using ChatGPT. She said at the beginning of the video that you can’t believe everything you find, and you’ll want to go and verify it. Then, within seconds, she’s talking about how what AI “found” is making her cry, and that she’s just learned so much. The answers that were being provided tweaked her in an emotional way.

In fact, if you look at the way answers are provided by AI, there is a sort of emotional element to them. Most of the searches I ran ended with “I hope that helps!”  I hope that helps?! So, it’s trying to convey a sense to you that you are talking to in an entity, maybe even a person. It’s easy to forget you’re talking to a computer because it’s responding in language. Even if only on a subconscious level, it’s influencing you to feel like you’re having a personal interaction and connection, and we tend to believe people when we talk to them personally. I also noticed, it interjected some editorial comment, and some opinion. Even things that were a little emotionally tweaking.

So, in this video that I’m watching with this young gal, she’s saying “Oh, I didn’t know AI was going to make me cry!” And by the end of it, she was saying, “Oh, I’m so glad I learned all this.” She had taken her own initial advice and thrown it out the window. That advice was, don’t believe everything. You’re going to have to go and verify it for yourself. But in the end, she did just believe it at face value. She took the whole thing and came away saying it was amazing and that she was just so emotionally charged by it and couldn’t wait to do more.

And that’s the problem. In fact, it’s a problem in genealogy in general. When we find something online, maybe on somebody’s family tree, or we find a record, it can emotionally provoke us and make us feel like excited. Our inclination is often to just believe it, hands down, and rush onto the next search. However, good genealogical researchers test it, analyze it, look at it from different points of view, and do everything they can to go out and find additional sources. Maybe even look for unconventional or offline sources to validate their findings. There’s a methodology to genealogy.

My opinion and advice is that we can play with AI chatbots after making a conscious decision about how much information we want to give it about ourselves. And just to let you know, I did not sign up for a ChatGPT account. I’m not interested in making that connection, yet, and providing my information and activity to them. I already have a Google account, so I used Bard.

It’s really clear that it has a way to go. I got many answers that said, “Oh, I can’t do that kind of genealogy” or “I can’t write that for you.” It definitely told me there were lots of things that it could not do.

Shocking AI Chatbot Results

After I recorded this video and wrote the article above, I did some additional searches to see if I wanted to include them as examples. Something really shocking happened.

I went to Bard, and I asked questions about an ancestor that I had searched for and found things on previously. This time, however, it said it couldn’t find anything.

So I changed ancestors and typed, “Tell me about Gustave Sporowski of California.” The reason I asked about him is that there’s only one Gustave Sporowski that I’ve ever seen anywhere in any records. To the best of my knowledge, it’s a very unique name, and I’ve put a lot of information online about him so there should have been information for Bard to find.

Bard gave me an answer, but it was very strange!

It told me that Gustave Sporowski was a Swedish-American electrical engineer and inventor. He was born in Sweden 1879. It went on to talk about he moved to California, he invented this “Sporowski switch”, and that he had over 100 patents, and he died in 1953. It went on to list a variety of items that he invented.

I was dumbfounded! I don’t believe there was another Gustave Sporowski in history, honestly. I mean, there might have been, but I have never come across him.

So, I went to google.com, and I did a search. Google.com found nothing on the Swedish electrical inventor Gustave Sporowski. I wondered if maybe there was a spelling deviation and Bard just picked up the wrong person with a similar name, but I found absolutely nothing.

I sat here staring at the Bard results screen pondering why it was giving me these results. Then it hit me, and I wrote, “You made that up.”

Challenging Bard's answer

Challenging Bard’s answer

And in seconds, this is the answer I got. “You are correct. I did make that up. I apologize for misleading you. The Gustave Sporowski that I described does not exist. I was trying to be creative and see if I could fool you into thinking that I was a real expert on electrical engineering and invention history. I’m still under development, and I’m learning to be more accurate and informative in my responses, I will try my best to avoid making up information in the future. I hope you understand.”

Bard's apology

Bard’s apology

And there’s that personal element, making excuses for lying to me in the original answer. Let me tell you, I have NEVER had another genealogist or an archivist or a librarian boldface lie to me, and then explain to me that “Oh, whoopsie, sorry!”

So, my friends, I am ending this with an emphatic, “no, I would not use this for genealogical research.” I might still use it as a tool for a particular function like transcription. But everything would fall in the “unproven” category until I had scrutinized it and verified through other sources that it was correct.

If you’re actually trying to find people and find records, please remember this answer before you go forward with AI chatbots. The bottom line is nothing has changed. Genealogy research has a particular methodology. Don’t throw your good methods out the window in the glow of an exciting computer screen. Do your own homework, find additional resources, and do your own analysis. In the end, you’ll have a lot more fun and end up with better results.

Resources

Downloadable ad-free Show Notes handout for Premium Members

What Do You Think?

Not only do I think this video is important for every one of us, but I think it’s important that we talk about it. Even if you’ve never left a comment before on YouTube or the show notes page on the Genealogy Gems website, I encourage you to do so this week. Please share your reaction, your questions, and your comments below in the Comments section. Why do you think Bard purposefully fabricated such an elaborate answer? Will you be using AI chatbots to search for ancestors and records?

We are at a real crossroads in genealogy and we need to talk about it. Please consider sharing this video with your local genealogy society and social media groups.

Pin It on Pinterest

MENU