Wednesday, November 4. 2009Google, Bing, Twitter and Instant Web Search
I read an interesting article this morning entitled Companies race to offer instant Web search, including Twitter by USA TODAY reporter Jon Swartz . The recent announcements that Google and Bing will include Twitter in search results raise some intriguing questions – and challenges. Ever seen a Tweet like this?
hmm tink nid >2 twitter acs; els msgs all jumbled up btwn personal & thots! dilemma! What search methodology is going to pick that up? Why, why not and who cares? And what do you do with it anyway? Given Twitter information is publicly available, it makes sense that using natural language search is extremely valuable for finding information - whether you are monitoring brand information or looking for answers. I bet that one large US airline would love to see the many, many YouTube hits about breaking a musical instrument go away! The fact still remains that you will get a lot of search results that you still have to deal with. Say you work for Target, and you want to monitor the Twittersphere. Try searching Twitter for the word "target". Results may include target run rates for the recent NZ cricket test match, the US retail store, target marketing references or target practice. A quick search on "target" on thesaurus.com shows target used as both a noun and a verb. Target is also a proper noun. A graphical link from thesaurus.com to visual thesaurus gives a hint of the many ways the word target can be used. Including text analytics capabilities means you can group similar documents together, thus creating categories around the document meaning. This allows you to automatically weed out the information you don't need and get to the information you need. Furthermore, the inclusion of text analytics in social media analysis means you can analyze comments, determine relevance, find promoters, detractors and much more! Stay tuned as we explore this topic more – it’s not going away! Comments
Display comments as
(Linear | Threaded)
Very interesting article. I have been working with SMSes, mining, classifying, gathering BI, etc. and understand exactly what you mean. Looking forward to more blogs as you explore this topic further.
If people post their resume in Google, Twitter, etc. how could you cluster skill-sets and experiences mentioned in those resume, after they are extracted, using text analytics techniques. What applications would you use? Any vendors out there, alreday offering such semantic matching on resume text contents?
There is a lot of different research going on in the job postings/resume matching arena. I'm intrigued by how search centric resume matching has become. The skill for a job applicant is not only to write a concise resume, but to use terminology that will match a hiring company's query! There are companies out there using semantic matching on resumes. We have found that to get higher accuracy, it is helpful to split resumes into sections such as Summary of Qualifications, Professional Experience, Education, etc. Applying ontologies/domain specific dictionaries to match different terms/phrases used in the same context can also be useful for matching say "text analytics", "text mining" and maybe even "natural language processing" as interrelated areas. If I submitted a resume for a postion that was looking for "text analytics" experience, does a standard search consider "text mining" as relevant? It would be a shame to miss out on potential candidates because a search query doesn't capture this information. Search relies on you knowing what you are looking for, text mining helps you discover things you wouldn't have thought to look for. When it comes to a job search, most employers are looking for candidates that stand out. Surely a combination of search, text analytics (both rules definitions and discoveries) would provide the best of both worlds.
|
ABOUT THE TEAM I'm Manya Mayes, SAS Chief Text Mining strategist. On this blog, my colleagues, friends and I discuss unstructured text and understanding the voice of the customer. Plus a few more things. Read more about me and the other contributors here. ContributorsQuicksearchSyndicate This BlogShow tagged entriesa2009 advertising alone analytics artifical intelligence auto burden conference consumer opinion content categorization Crime criminal CRM customers denmark Discussion Forum email event extraction extraction FBI global forum information retrevial interview data john elder kdd M2009 manufacturing misspellings safety sas sentiment sentiment analysis significance Skittles social media social networking success stories supervised learning svd synonyms synsets teragram teragram; sas global forum; twitter; demo; text text mining textspeak topic detection Twitter visualization YouTube
|
Yesterday, Seth Grimes posted a fantastic article on Text Data Quality yesterday. A must read for anyone in this space. The article points to some of the text quality issues I have mentioned in my last two blogs. Text is in a league of its own when it
Tracked: Nov 18, 13:34