Guest Post: Lisa Gan on Sentiment Analysis

Hey guys,

Sorry it’s been a while since I posted anything. Been very busy building visibility of Mind of Man, the awesome App I’ve been working on at 2Paperdolls.

Here are some articles that were posted recently on Gamasutra and Game Trailers! Also feel free to check out the MOM trailer, If you haven’t seen it yet. It’s lovely!

Lately, I’ve been getting a lot of requests for guest features but this one really piqued my interest. Working on Mind of Man has gotten me really interested in the field of Sentiment Analysis and it’s various potential applications. Lisa Gan contacted me with this piece, which I thought was very well written and informative. Enjoy 🙂

Innovative Social Media Technology: Sentiment Analysis by Lisa Gan

“Sentiment analysis represents an innovative way to examine emotional trends across Internet content, and is of particular value to social media networks and affiliate marketers. A sentiment analysis involves looking at the kinds of attitudes implicit in different documents and messages, with the intention of judging overall trends and moods from positive to negative. This kind of analysis works around a scale of emotional responses, and looks for repeated phrases and the structure of messages to try to determine the mood of the writer.

Computer programs have made sentiment analysis more able to target larger amounts of data over time. While lacking the kind of subjective scrutiny of a human reader, semantic analysis programs and Natural Language Processing can identify repetition and key variations in phrases. These programs can be configured to be partly automatic, and to rely on some human input to work out the subtleties of individual phrases. Where computer sentiment analysis works best, then, is in dealing with, and creating metrics for, the kinds of phrases and words used in large data sources.

How can it be applied to social media?

The value of sentiment analysis for social media networks is relative to the ability of data mining and metrics to make advertisers know how best to target consumers. By performing sentiment analysis on reviews, comments, and responses to a product or service on a Facebook page, it is possible to identify how far people react positively or negatively to a trend. By looking at a large amount of data, the overall response of an audience can be evaluated and compared across a number of different media. Social networks, which involve a lot of freely offered content and opinion, are good ways for marketers to engage with and use feedback for future campaigns and product designs.

Business Advantages

Some of the key benefit advantages for sentiment analysis demonstrate why it has become a useful tool for marketers and businesses over time. Primarily, by analysing a lot of data via keywords and phrases, it is possible for a company to quickly sort through and produce metrics without having to deal with a lot of human analysis. Bringing up a general picture of trends, and then being able to focus on specific parts and highlighted words can be used to track patterns in consumer response to a brand. Understanding this reception can allow a business to work to fix negative brand comments, and to try and trace back a repeated phrase or trend by date and clusters of comments to a particular person.

Business Drawbacks

Of course, there are drawbacks to sentiment analysis that haven’t quite been solved. The clearest is that a computer program cannot always read subtleties in terms of sarcasm or irony, and can only provide a surface sense of trends, rather than detailed market research. However, by combining human input with automated tools, it is possible for social media networks and marketers to build at least a general picture of how responses to a business and products are being shaped, and how to respond to them.”

Author: Lisa Gan is a technology enthusiast with a particular interest in IT and social media. She collaborates with Computrad  – managers in IT services, specialising in IT outsourcing.

About Paddy Badger

Former games developer at Open Emotion Studios/Time Machine Games. Film-Maker. Over a dozen shorts as writer/director including Cuppa, Retribution and An Beanshi. Director of indie cult success, The Three Don'ts - winner of over a dozen awards worldwide.

Posted on August 3, 2012, in 2PaperDolls, Guest Post, news, Observations, Sentiment Analysis and tagged , , , , , , , , , , . Bookmark the permalink. Leave a comment.

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: