Opinion Mining

Opinion mining is a type of natural language processing for tracking the mood of the public about a particular product.

Opinion mining, which is also called sentiment analysis, involves building a system to collect and categorize opinions about a product. Automated opinion mining often uses machine learning, a type of artificial intelligence (AI), to mine text for sentiment.

Opinion mining can be useful in several ways.  It can help marketers evaluate the success of an ad campaign or new product launch, determine which versions of a product or service are popular and identify which demographics like or dislike particular product features. For example, a review on a website might be broadly positive about a digital camera, but be specifically negative about how heavy it is. Being able to identify this kind of information in a systematic way gives the vendor a much clearer picture of public opinion than surveys or focus groups do, because the data is created by the customer.

There are several challenges in opinion mining. The first is that a word that is considered to be positive in one situation may be considered negative in another situation. Take the word “long” for instance. If a customer said a laptop’s battery life was long, that would be a positive opinion.  If the customer said that the laptop’s start-up time was long, however, that would be is a negative opinion. These differences mean that an opinion system trained to gather opinions on one type of product or product feature may not perform very well on another.

A second challenge is that people don’t always express opinions the same way. Most traditional text processing relies on the fact that small differences between two pieces of text don’t change the meaning very much.  In opinion mining, however, “the movie was great” is very different from “the movie was not great”.

Finally, people can be contradictory in their statements. Most reviews will have both positive and negative comments, which is somewhat manageable by analyzing sentences one at a time. However, the more informal the medium (twitter tweets or blog posts for example), the more likely people are to combine different opinions in the same sentence. For example: “the movie bombed even though the lead actor rocked it” is easy for a human to understand, but more difficult for a computer to parse. Sometimes even other people have difficulty understanding what someone thought based on a short piece of text because it lacks context.  For example, “That movie was as good as his last one” is entirely dependent on what the person expressing the opinion thought of the previous film.


Importance of Sentiment Analysis

By using Social Media, your organization can learn what your customer truly thinks about you, your products and your services. A key component to your Social Media Analytics program should include understanding the point of view of the author of the post. You need to analyze whether the post is positive or negative.

Determining? Whether the opinion of a post is not easy, but technologies such as Natural Language Processing, Computational Linguistics, and Text Mining have made it a little easier. These technologies take care of the heavy lifting, making your Social Media Analytics process a little less consuming. It can be a consuming process.

Natural Language Processing (NLP) software endeavors to understand groupings of words to determine their meaning. In the case of Social Media Analytics, NLP tries to understand the sentiment of the word groups and rate them as either positive or negative. The problem comes in with understanding and ambiguity. Take for instance this simple example to help you understand one of the problems with NLP. Take the phrase The house is small. Is that a positive statement or a negative one? Well, it all depends on the reader and what you are looking for. NLP is not perfect, yet but with a little manual work it can get you to where you need to be. Social Media Analysis will for some time be a semi-automated process because there are some things that software just can’t figure out.

Still, the ability to understand sentiments is an important factor. Understanding sentiments help towards understanding the ROI of your Social Media initiatives. By setting a baseline of where your customer sentiments are today as collected through your Social Media Monitoring data-warehouse then over time watching how those sentiments improve can serve as a useful key performance indicator (KPI). Then you can tie the timing of the sentiment shift with sales for the same period and now you have a measure that most executives will appreciate.

As you continue you Social Media Analytics process do not forget to collect and benchmark the sentiments of social web participants.

– Do you have the ability to become a mystery shopper? Find out..