16 Jun

This image shows that it is humanly impossible to deal better with all customer sentiment.’Sentiment Analysis’ came just in time.

It could be you: an entrepreneur who is running a business but is grappling with understanding your customers, especially what they need or want. Or even worse, you don’t have a clue of what your customers think about your new product or service in the market. Sentiment Analysis (SA) is just what you need.

Sentiment Analysis is a 21st Century solution for business owners, SMEs and entrepreneurs who want to understand their consumers. It is essentially the use of natural language processing, text analysis and computational linguistics to identify and extract subjective information in source materials.

Gateway to marketers
SA is a gateway to marketers, business owners and decision makers where they can identify and understand their consumers’ feelings and attitudes toward their brands or products in online conversations like blogs, emails, forums, Facebook posts, likes, comments, tweets, reviews, wikis, etc.

Analyzes more than just words
Instead of just analyzing words, sentiment analysis identifies the customer’s attitude towards a brand by using variables such as context, tone, emotion, opinions, just to mention a few. It also classifies the polarity of a post, comment, or statement which determines whether sentiment around a topic is positive, negative or neutral.

Businesses that practice sentiment analysis do so through social media monitoring software which use statistical, machine learning and natural language processing techniques to automate sentiment analysis on vast amounts of social data.

SA and business intelligence
Sentiment analysis and ‘social’ data enables business decision-makers to understand consumer’s attitude and behavior more than ever before. Sometimes, it can be difficult to find out valuable information in surveys from people who didn’t buy a product or service. The ‘social data’ allows one to understand information circulating around the whole industry.

SA and digital space
With sentiment analysis, it is possible to search the digital space for opinions, reviews, posts, and tweets around the competition. This is user-generated insight that you can collect for product positioning.

The all-Knowing SA
Some of the questions one can answer from sentiment analysis about a business may include how people feel about a product or brand,how they are responding to campaigns/advertisements or product launches.Whether there is a way to predict the outcome of a campaign or event so that one can know how to invest better in marketing.
Other concerns could be: Why aren’t consumers buying our product?Based on a sample of tweets, how are people responding to this ad campaign/product release/news item?Is this customer email satisfied or dissatisfied?Are customers happy with our customer care representatives?

Tools and software
With the advent of Big Data, sophisticated computing technologies have been developed to deal with the challenges brought about when processing this data. While most of them are commercial and very expensive for SMEs, there exist some open source alternatives which can be customized for a business to serve the purpose of harvesting and analyzing social media data.

One such open source software is Apache Hadoop Framework. Hadoop has modules that cater for data scraping, machine learning, natural language processing, visualization and much more-and can be obtained for free and be customized to suit the business needs. Custom algorithms can also be developed using tools such as R, Python, Julia and so on.

Other SA application areas
Apart from business applications, sentiment analysis can also be applied in other domains, including:
•Politics – for mining public opinions and political temperatures
•Law and policy making
•Sociology and
•Psychology

Written by Vincent Mosoti,a Masters Student in the School of Computing and Informatics and a Researcher in Computational Intelligence (vincent@vmosoti.com)