4 May 2011
Why Semantic Analysis Trumps Sentiment Analysis

For years, sentiment has been a widely used measure of how customers view a company’s products and services. But sentiment analysis has inherent flaws. First is what it cannot tell you because it only considers a small amount of the available data. Only about 25 percent of posts actually contain sentiment, either positive or negative, which means three out of four posts are neutral, revealing no sentiment, and are effectively being ignored by the analysis. Thus, decisions are being based on what only a quarter of the posts are saying.

Another problem with sentiment is statistical confidence in the data. Simply stated, all methods of sentiment analysis rely on example data that, whittled down, reveals a low level of confidence about the sentiment being identified, either positive or negative. Data with such low confidence is a poor foundation for sentiment analysis.

Bottom line — sentiment analysis is not inherently bad. In fact, for particular types of questions, it may be the right approach. But if you use it, you need to be sure that it’s the right tool for the job, that valuable data is not being ignored, and that the method of sentiment analysis is built on sound data.

A much more statistically reliable approach is semantic analysis — a way to distill and create structure around mountains of unstructured data, such as blog posts, social network chatter, tweets and more, without preconceived ideas of whether or how they are related.

Semantic analysis allows you to cluster different data elements based on similarity, rather than preset classifications such as positive, negative and neutral. This helps you uncover important information like what exactly people are saying about your product or service; where and how they use it; and enhancements or new offerings they’re interested in. This type of valuable information can drive product development, new revenue streams and strategies for marketing, advertising and media planning.

Social media information is expanding at such an amazing pace, organizations need new and innovative ways to capture “nuggets” of intelligence it can reveal. Semantic analysis can help harness and make sense of all that information — in exponentially more powerful ways than sentiment analysis. In fact, a valuable type of semantic analysis is topic discovery: the summarization of large amounts of text by automatically discovering the topics and themes within. Networked Insights’ new Topic Discovery Engine (TDE) is a semantic analysis system finely tuned to discover topics in social media posts.

Most exciting, with semantic analysis you have tremendous latitude about how you approach the analysis. You don’t have to be certain about what you’re looking for. How many times in your life can you say that lack of certainty gives you a leg up? With semantic analysis, you can let the social media speak for itself, revealing to you amazingly accurate and important information that can inform critical decisions.

Click here to read our full report on Semantic vs Sentiment Analysis.

Share

About Dan Neely

Dan Neely serves as Networked Insights´ Chief Executive Officer. Dan brings to Networked Insights over 10 years of entrepreneurial, management, operational and with technology, manufacturing and services companies. He is an expert in customer intelligence and has hands on experience with the challenges companies face in gathering relevant, real-time insights about their customers.

3 thoughts on “Why Semantic Analysis Trumps Sentiment Analysis

  1. Pingback: Sentiment Analysis v. Semantic Analysis - semanticweb.com

  2. Seth Grimes

    I believe you misconstrue sentiment analysis. Just about any decent sentiment-analysis implementation is going to use natural-language processing techniques for both syntactic and semantic analysis, in order to discern sentiment and its object (whether a named entity or a topic or concept) and the opinion holder, and any more progressive tool is going to support classifications beyond positive/negative/neutral tonality.

    Further, neutral is useful information in some business applications.

    Seth, http://twitter.com/sethgrimes

    Reply
  3. T.R. Fitz-Gibbon

    Thank you, Seth, for your comments. I completely agree with you: any sentiment analysis implementation should use Natural Language Processing (NLP) for both syntactic and semantic analysis. However, the extensive analysis we performed for this paper focused on the sentiment problem itself, not one particular solution to it.

    Whether one uses a sophisticated automated solution (relying on NLP, Machine Learning, etc.) or relies on a manual approach (having people read and classify sentiment), we believe there are fundamental issues with the way the sentiment problem is phrased. If one is not careful, sentiment analysis can ignore a majority of the available data and the results can largely be left up to chance. The cause is the inherent subjectivity of sentiment analysis. These conclusions come from a statistical analysis of the sentiment problem itself and apply (at least in some degree) to all solutions.

    Sometimes sentiment analysis is the right tool for the job. However, it is important to understand when it is the right tool because ignoring data and measuring chance more than anything else can drastically reduce its value.

    As for your other points, the value in moving beyond the positive/negative/neutral categories and the value of neutral posts are essential points to our paper. Variations on analyzing positive and negative posts is the type of sentiment analysis requested most often, in our experience. We strive to show our customers what is possible when we move beyond that narrow view of meaning.

    Reply

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>