We have our product #Reviewdede where people give reviews of movies, TV serials & Short films.These Review are perfect source of analysis which gives viewers insight thought about movie, TV shows or short films. We put some Sentiment analysis on these reviews ...
We tried to use #Watson Natural Language Understanding , a suite of NLP capabilities that makes possible to quickly and easily extract and analyse metadata from unstructured text.
It provides sentiment & emotion of text with deeper analysis of text.
Analyze the sentiment toward specific target phrases and the sentiment of the document as a whole.
Analyze emotion conveyed by specific target phrases or by the document as a whole.
and there are more capabilities of watson.....
Example i have provided data of user's review and critics review of "Accidental Prime minister"
Over all sentiment of review score is average in positive
Which looks similar if we see the movie review on other media
Overall Emotion from entire Review
Previous analytical tool only cared about review is positive or negative but now emotions of text , entities used like which is the most used object, people, companies, cities, geographic features were in reviews. we can derived that user liking for particular entity and predictability for next movie location , casting. topic
Like we did analysis of another movie #Tubelight look at the deep analysis of document . More review text more stronger outcome . data-driven insights provides clients to drive deeper understanding and better decision-making. This knowledge base is the gift that keeps on giving, because it continues delivering new intelligence depending on who is looking at it, and what they are looking for.
So think how much beneficial these analysis for Cast creator.. movie content writer.. what if content management systems also become cognitive with context of these user's liking .
How much more powerful insight will it be if social media and all other review platform merged?