July 19, 2017 11:54 pm

What is Sentiment Analysis Solution

OLSPS Analytics’ Sentiment Analysis Solution is a natural language processing (NLP) model designed to reveal valuable information on current market sentiments. Through text mining and computational linguistics our solution is able to analyse extensive amounts of text on social media platforms and derive opinions towards certain subjects, items or events. In addition, Sentiment Analysis Solution goes one step further and establishes the source generating these sentiments. 

Benefits of the Sentiment Analysis

Benefits of Sentiment Analysis in Commercial Sector:

A company may benefit, in many regards, from deeper insight into public opinion. For instance, firms with positive feedback can use our solution to continuously monitor customer satisfaction and their perception of different goods and services provided by the company.

Alternatively, in the case of companies with negative market sentiments, identifying the key sources to these attitudes, Sentiment Analysis can help address these issues with the highest level of efficiency by optimally allocating resources to resolve the problems.

Benefits of Sentiment Analysis in Government Sector:

Sentiment Analysis has become very popular solution for political campaigns. Even though short text strings might be a problem, sentiment analysis has shown that Twitter can be seen as a valid online indicator of political sentiment. Tweets’ depicting political sentiment demonstrate close correspondence to parties’ and politicians’ political positions, indicating that the content of Twitter messages plausibly reflects the offline political landscape.

How does Sentiment Analysis work

OLSPS Analytics Sentiment Analysis Solution gathers text from various sources (for example social media) and places them into a structured database where they can be used for analysis. This raw collection of data is stored in the form of text, which is known in the analytics world as ‘unstructured data’; data which is typically very difficult to use in any analysis. However, the solution developed by our team uses Text Mining, a set of intelligent algorithms, to derive meaning from this unstructured data.

A simplified description of Sentiment Analysis process:

    First, the sentences of all the assembled text are divided into their separate parts of speech.
      The solution is then able to highlight the groups of words, which convey sentiment, as well as identify the various entities associated with them.
        Once this preliminary process is complete, these groups are assigned positive, negative or neutral sentiment scores and a weighting depending on the degree of sentiment expressed.
          The scores are then aggregated on an entity level in addition to the document as a whole.
            Further analysis is conducted taking into consideration the context these words were given. In this way, the raw text is turned into structured data, which allows for more generic statistical analysis.
              The results produced by this final step sheds light on very specific, as well as more general sentiment sources and opinions borne by people towards the reviewed subject matter.
                The results produced by this final step sheds light on very specific, as well as more general sentiment sources and opinions borne by people towards the reviewed subject matter.

              Sentiment Analysis Solution Case Study

              Nedbank is one of the four largest retail banks in South Africa based on the number of customers.  With such a large customer base, it becomes critically important to monitor the customer sentiment at any point in time. With this in mind, Nedbank approached our team to help them to develop a social media monitoring tool based on IBM SPSS software.

                Sentiment Analysis Solution tool enables Nedbank to collect data on the online interactions that the company has with its clients across a variety of different social media feeds including Twitter, news feeds, blogs, Facebook and other relevant sites.  The online interactions are then categorised and turned into ‘structured data’ (through the process described in the section above) which are then used for further analyses.  In this specific scenario, the data is used in the Nedbank solution to drive customer engagements and upsell opportunities.  There is also potential for the data to be used in predictive models to drive customer retention and other goals.