Writing today to mention a free webinar Anderson Analytics is offering together with SPSS. Jesse Chen, Senior Consultant at Anderson Analytics will explain how a sound methodical approach–along with creative tips and tricks–can help you analyze unstructured data with better results.
Over the past three years we have developed several techniques, methodologies and best practices (AA-TextSM) in text analytics. One of the software companies we have partnered with is SPSS, Inc. Anderson analytics uses several of their analytical tools including SPSS Clementine, Text Mining for Clementine, and SPSS Text Analysis for Surveys. This presentation will focus on the capability of one of these popular text analytic tools, SPSS Text Analysis for Surveys.
Jesse will be using some of our real-world case study examples of how Anderson Analytics has saved our clients time, money, and enriched survey insights using these keys to text analysis. The one-hour webinar will take place at 12pm ET on March 20. The webinar is most relevant for those having an interest in text analytics, particularly managers & analysts who conduct studies that routinely obtain lengthy text data.
If you’re interested feel free register here.
- Tom H. C. Anderson
5 responses so far ↓
1 Blog Business Summit » Mining Online Sentiment: Can Algorithms Alone Really Tag Blog Posts Accurately? // Mar 14, 2008 at 5:24 pm
[…] me. No doubt that boosts accuracy. Tom Anderson’s blog is here, and he discusses an upcoming webinar on the […]
2 Tom H C Anderson // Mar 15, 2008 at 11:04 am
If you are working with longitudinal data, comparing month to month for instance, or comparing different products and brands then extremely accurate sentiment reading isn’t necessary as you are really looking for differences between groups. Additionally by considering the relationship between positive and negative sentiment in trended data (they tend to be positively correlated) when the correlation changes, in other words in one month for one brand you might see that negative sentiment increases while positive decreases, this signals a possible ‘event’ is occurring which needs to be drilled down into for further investigation.
However, for some of our clients in the past (such as Unilever), an extremely accurate level of sentiment was desired. Our methodology (AA-TextSM) relies on triangulation for validation, and we have sentiment accuracy in high nineties in most cases when applying this technique. Because most of our projects are ad-hoc in nature, the human factor is very important, so Anderson Analytics, more so than those companies focusing solely on a large volume of blog posts usually invest the time in perfecting custom dictionaries and understanding the special relationships between words in each project.
As you mention, many survey open ends are rather structured. On the other hand many are not. For instance if you ask a hotel guest to rate their overall satisfaction on a 10 point scale, then ask, why did you give this rating in an open ended question, you will get anything but structured answers. Our methodology has been used on other types of data as well though (call center logs, emails etc.).
-Tom
3 Blog Business Summit » Automated Sentiment Detection Round 2: 80% Accuracy Confirmed for Blogs and Unstructured Content // Mar 15, 2008 at 7:29 pm
[…] addition, Mark Anderson responded to my post yesterday with a comment on his own blog. Anderson clarified: “If you are working with longitudinal data, comparing […]
4 Tom H C Anderson // Mar 16, 2008 at 10:19 am
Yes, there is definitely “non trivial” expert human involvement in AA-TEXT. Though some of the learning we have discovered using the methodology could be fed back into a more automated process in the future…
Naturally anything that can bring sentiment accuracy up would be useful. I am rather skeptical when software vendors currently make claims at above 80% accuracy using automated systems without human involvement.
-Tom
5 pdlhywqtk ebkwg // Jul 10, 2008 at 8:41 am
jbvqz zkwryp bovlaf nckufetdi rtsuaoh uskyv tpjlkiefs
Leave a Comment