Skip to content

Machine Readable Data

November 17, 2011

How do we analyze news articles, blogs and tweets into actionable information that can be used in a matter of seconds?
        I have thought about this and I read couple of papers, solutions and I came up with this Logical Data Model that definitely can be used to convert news into machine readable data, assign numbers, sentiments about the specific topic related to news story and assign a score which would give any company or analyst quantifiable values that can make better and instant decisions.
        The design is robust so that we can have a list of words in any language, news stories of any type on any topic.

Here is how I would approach the analysis:
1.) Load the static tables such as WORD, TOPIC, NEWS TYPE, LANGUAGE, which are optional in the physical implementation world and WORD TOPIC which is very important for our analysis.
2.) Search Twitter, Newspapers etc. for text, stories, and blogs and load them up to NEWS STORY
3.) Sort the news by the Topic that we are trying to do analysis on.
4.) Create a scorecard to rank these stories in NEWS STORY TOPIC by looking up the WORDS’s sentiment in the WORD TOPIC
5.) Summarize for each topic
6.) Compare the story sentiment with some satisfaction or competition out there, or even measure that against product prices etc.
7.) Pinpoint the problems and draw conclusions

        The Natural Language Process would parse and categorize the text which produces metadata with any number of factors such as whether the story is important to this company or how relevant this is to this company etc.

        Now, I know it’s easier said than it’s done, but that’s how at least I would approach this process.
If anyone is interested in obtaining the DDL, just let me know and I will send it to you.

No comments yet

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: