Sample result image from First Impressions

I am excited to announce the IMA’s launch of First Impressions, a new tagging feature on our website. This new feature gives you an opportunity to tell us what grabs your attention when viewing items in our collection, without typing ‘text-based’ tags.

As we have developed this project, I have realized this is a really fun way to interact with the objects in our collection. As each work is displayed, you are asked to click on what first draws your eye. After clicking through the whole set (this time it is about 12 images), you will see each image with an overlay, showing where you clicked and where everyone else clicked. Your click will be displayed as a small black marker on each image. Everyone else’s clicks will display in a heat map- an array of colors showing the most clicked (and most noticed) areas of each work. The darker the shade of red, the more clicks have occurred in that area.

We are planning to make this an ongoing series with new sets of works to view in the future. Each time we release a new set, we will post about it. We also hope to post results from previous First Impressions sets showing you what people see- and also what they don’t see.

With much of the US already experiencing winter weather, we were inspired to gather up chilly images inspired by Winter Solstice. This set reflects the change in the seasons and the weather to come over the next few months. So grab your favorite warm beverage (I prefer hot chocolate this time of year), come in out of the cold, and give us your First Impressions.

Click here to get started

These are the steve tagger’s top 100 most contributed tags. The red ones happen to be a few of those that I’ve entered. You might notice that some of them look a little funny, like lightgray. This is because we use a normalization process to equate words that are essentially the same. For example, consider these tags on The Boat Builders by Winslow Homer:

The Boat Builders, Winslow Homer

A term like “New England” may have been entered with proper capitalization, or with all lowercase or uppercase characters. To treat these entries as the same basic concept, we normalize them to “newengland”. Similarly, some folks might type a term like “seashore” with a space, and other folks without a space. We recognize that sometimes these minor differences make a significant difference in the meaning of a term, so we keep all of the original tags as they were entered. This normalization handles most cases properly (further research into the occurrence rate of special cases continues in the Text Tags and Trust project), and it allows us to display objects that have been tagged with all variants of a term when it is clicked in the tag cloud.

After handling simpler transformations like whitespace removal and lowercasing, the next step we’re interested in taking is lemmatization. You can see a few examples where this can be done in the tag cloud above… the term “rocks” can be lemmatized to “rock”, and “children” to “child”. By adding another normalization routine which takes this extra step using a lemmatizer from the Natural Language Toolkit (which makes use of the WordNet database’s built-in morphy function), we can generate the following tag cloud for this painting:

This may just be my perspective, but I find that the lemmatized version really gives a better sense of representation, uncluttered by redundancy. We’re still doing some fine tuning, and looking into how to handle terms with multiple words. Our partners at the University of Maryland are doing some research to figure out how we might define heuristics to handle multiple word terms (e.g. a rule that says we should lemmatize the second word of an adjective-noun pair), based on the collection of tags that we currently have.

As we study the results, we will definitely be considering scenarios where this sort of normalization fails to recognize nuance and gives misleading results, and how to handle this both in our research and in user interfaces. It’s a tricky problem that is sure to lead to many interesting questions and findings about folksonomic linguistics to discuss in the future.

That’s why I was pretty intrigued by a new tool called Moody that lets you “Mood Tag” your iTunes playlists with how these songs make you feel.

What a great idea! With this tool you simply click a colored square to assign a degree of “mood” to each song as you are listening to them. This morning I was air drumming along to “Lucretia MacEvil” on my way into work… Personally I’d tag that with Intense and Happy! However, chillin’ out with my Sunday morning paper and cup of coffee seems to be more in line with some Stan Getz bossa nova grooves (i.e. Calm, Happy).

Here at the museum we’ve been working on ways to use social tagging to help people find our art more easily and to be able to describe it in their own words. You can see this in action by checking out any of our artworks online. One with some great tags is “Young Woman in Blue” by Edgar Degas.

You can also checkout our TagCloud and click on any term to find other art from our collection that users have tagged. I think this can be a great way to stumble onto new works of art that you might otherwise have a hard time finding with a search tool.

I think it would be really interesting to start collecting thoughts from our visitors about what their emotion or moods are related to particular pieces of art as well! Moody gets it right by using the squares as a metaphore for mood instead of making people come up with their own words to describe this. This sort of non-text based tagging will be really useful as we try to come up with new ways of using the social tagging data that well collect from our visitors.

There are several of us in the museum community thinking about ways to use social tagging and what it means for museums to solicit information from and listen to their users in these ways. IMA and a group of other instiutions has been funded to do research into this as part of a project called steve.museum (http://www.steve.museum) Please check out the website for more information!

Or better yet! Help us with our current round of tagging experiments! You can pop on and tag some art by registering at http://tagger.steve.museum You’ll be shown some art from a number of world class institutions and asked to tag them with your own descriptions. Your tags will help us better understand how we can use these methods to make art easier to find and more engaging in an online setting. Thanks!