Sentiment analysis
Discussion of sentiment analysis, which is the extraction of indicators of a writer’s (or speaker’s) opinions and emotional reactions (e.g., about a product feature or brand). Related subjects include:
Predictive analytics vendors’ text mining sophistication
Steve Gallant of KXEN contacted me over the summer to show me KXEN’s new text mining capability. It was pretty basic bag-of-words stuff, which is still a lot better than nothing, and actually fits pretty well with KXEN’s general simplicity-centric strategy.
This inspired me to check whether there had been any big changes in text mining capabilities at SAS or SPSS. It turned out there hadn’t. SAS is also still on the bag-of-words level. SPSS, however, does do sentiment analysis (pretty obvious, considering their focus on surveys and the like) and negation.
Thanks go out to Mary Crissey and Olivier Jouve for getting back to me when I asked, along with apologies for taking a while to post what they told me.
Categories: SAS, Sentiment analysis, SPSS, Text mining | Leave a Comment |
More on text processing in CEP
StreamBase isn’t the only complex event/stream processing (CEP) vendor doing text processing. Progress Apama is as well. Stemming, fuzzy matching, and so on seem to happen all the time. But there’s also at least one case where they flat-out do sentiment analysis. Edit: I presume this is in the investment market, as that’s where most of Progress Apama’s business is. Read more
Categories: Investment research and trading, Progress and EasyAsk, Sentiment analysis, Text mining | Leave a Comment |
Interesting comment thread on reputation tracking
Techcrunch blogged skeptically about Umbria’s* service, specifically its partnership with PR Newswire. The comment thread had a fair amount of pushback, largely from vendors with skin in the game.
*Note: Umbria has a non-obvious URL.
I haven’t actually spoken with Umbria — uh, guys, why not? — but they seem to have a reputation tracking service. Their niche is apparently to quantify/measure by a variety of metrics, and that’s supposedly what makes their service (and their competitors’) worthwhile. Read more