Real Estate Intent on the Web

The US housing crisis has been frequently reported as one major cause for the current financial turmoil. I was wondering whether indicators for the housing crisis can be found in Google’s Search Query Logs.

To look into this, I compared the search volume for the following explicit intentional queries: “buy a house”, “rent a house”, “sell my house” and “find a house”. The results are interesting, yet hardly surprising.

Tracking Real Estate Intent on Google Trends

” Buy a house” undergoes seasonal fluctuations, with peaks at the end/beginning of every year. Overall though, there seems to be a downward trend. At the same time, “sell my house” and “rent a house” are on the rise. “Find a house” is relatively stable, but slowly declining as well. Although subtle, the housing crisis can be identified in the data.

Google Trends seems to provide some interesting data (such as the one above), yet I miss some features and several questions remain unanswered. I’d love to see a mashup with Google Maps, where I can not only plot the queries over time, but map them on different regions of the US. Questions that I would like to have answered include: 1) What is the absolute search volume of queries? Google does not give a way the absolute number of queries per of interest. 2) Does Google account for rising query volume? I assume that the total number of queries issued in 2004 is significantly lower than the total number of queries issued in 2007. So does a decline in, for example, the blue curve refer to an absolute decline in numbers, or to a relative decline that factors in overall query volume increase? 3) “Sell my house” does not have any data before 2005 – what does this mean exactly? It seems odd that people on the web did not (or hardly) use the term “sell my house” before 2005 on Google.

Yet, the kind of analysis provided by Google hints towards potential applications of taking an explicit goal-oriented stance on the web.

Update (Oct 7 2008): It seems that Google Insights for Search covers many of the issues identified above. See the example here (you must be logged into your Google Account to see the numbers).

Capturing User Intent on the Social Web

Most traditional tags in tagging systems such as delicious focus on describing different aspects of the content of resources (what it is about), rather than intent (what it can be used for). In contrast to traditional tags, Purpose Tags focus on capturing aspects of intent, i.e. the different contexts in which a particular resource can be used.

When assigning purpose tags, users are assumed to tag a website with a specific purpose or goal in mind. To give an example: When bookmarking the website http://www.facebook.com, a user might tag the resource with a purpose tag “organize a high school reunion”. The intuition behind that is that purpose tags 1) expand the vocabulary of traditional tags and 2) help bridging the gulf between user intent expressed in search queries and the resources users expect to retrieve.

To the best of my knowledge, this type of tag is novel, i.e. it has not been studied in the context of folksonomies before, neither in theory, nor in practice.

To explore this idea, two students of mine have developed a purpose tagging prototype that I applied in an exploratory study on the subject. This study has produced a number of interesting findings. Most significantly, it shows that 1) users are willing and able to assign meaningful purpose tags in a semi-controlled environment and 2) that the vocabulary of purpose tags seems to differ significantly from the vocabulary of traditional tags.

Result of Folding the URL-Tag Network into a Tag Network

The figure above shows a purpose tag network, and nicely illustrates the difference to traditional tag networks. Where traditional tag networks focus on semantic relationships between tags, the purpose tag network seems to emphasize pragmatic relationships. For example, the purpose tag “watch the EURO 2008 in Graz” is related to “find public viewing places in Graz” and “find a place located in Graz”. Whether users are actually willing to assign purpose tags in contemporary social software applications remains open.

The results of this study, documented in a paper (Purpose Tagging – Capturing user intent to assist goal-oriented social search.pdf), have just been accepted for presentation at the Search in Social Media ’08 workshop that takes place in October in conjuction with the Conference on Information and Knowledge Management, Napa Valley, USA.

Meeting Reflection

The informal research meeting with Ralf Klamma‘s group at RWTH Aachen took place last Tuesday at TU Graz, and in my view the meeting was a great success. I’d like to thank everybody who attended, but particularly Ralf, together with his students Yiwei, Anna and Zina for preparing and giving interesting presentations and for allowing us to learn about their research. I’d also like to thank the students in my group, Mark, Christian, Monika and Maida for their hard work they put into their research and the presentations this week. I’d like to thank Marc for attending the meeting – it was great meeting him in person, as we have already collaborated in the past (the KASW’08 workshop).

I am also very happy and thankful that Henry and Andrew managed to attend this meeting as well. Their comments and helpful criticism were much appreciated – especially because their own research has been a great inspiration for our group in the past.

For documentation, we have made selected presentation slides available online.