Analyze the sentiment of social networks, reviews or customer satisfaction surveys
Have you ever wondered what people say about you, your company or your products in social networks? Have you ever tried to analyze the tens of thousands of free-text answers of a customer satisfaction survey?
Sentiment Analysis (also known as Opinion Mining) consists of the application of natural language processing, text analytics and computational linguistics to identify and extract subjective information from various types of content.
Advantages of automatizing Sentiment Analysis. Applications
The automatization of sentiment analysis allows to process data that due to their volume, variety and velocity cannot be treated efficiently by human resources. It is impossible to extract the full value from interactions in contact centers, conversations in social media, reviews of products in forums and other websites (in number of thousands, when not hundreds of thousands) using exclusively manual treatment.
The initiatives of Voice of the Customer (or Citizen or Employee) analysis increasingly incorporate these sources of unstructured, unsolicited and instantaneous information. Moreover, because of their immediacy and spontaneity, these comments usually reveal the true emotions and opinions of our audience.
The automatic Sentiment Analysis provides the ability to process high volumes of data with minimum delay, high accuracy and consistency, and low cost, which allows to complement the human analysis in several scenarios:
Voice of the Customer (VoC) and Customer Experience management
Analyze automatically all types of sources of customer insights (surveys, social conversations) and the interactions in the customer contact points.
Social media analysis
Easily build tools for social media monitoring and analysis featuring the ability to extract opinions on a massive scale and in real time.
Analysis of the Voice of the Citizen, Employee, Voter...
Analyze all sorts of channels to measure satisfaction (at work, with public services, social) and identify opinions, trends and emergencies.
MeaningCloud’s Sentiment Analysis API
Sentiment Analysis at attribute level
Our Sentiment Analysis API performs a detailed and multilingual sentiment analysis on information from different sources.
The provided text is analyzed to determine if it expresses a positive, neutral or negative sentiment (or if it is impossible to detect). To achieve it, the local polarity of the different phrases is identified and the relationship between theme evaluated, which results in a global polarity value of the text as a whole.
In addition to the global polarity and at sentence level, the API uses advanced natural language processing techniques to detect the polarity associated with both the entities and the concepts of the text. Besides, it also allows the user to detect the polarity of entities and concepts defined by himself or herself, which makes the service a tool applicable to any kind of scenario.
Highlights of our Sentiment Analysis API
MeaningCloud's Sentiment Analysis API combines capabilities that enable to optimize the accuracy for each application, thanks to highly granular and detailed polarity extraction features. These are some of their features:
Extract the general opinion expressed in a tweet, post or review.
Sentiment at attribute level
Detect a specific sentiment for an object or any of its qualities. Analyze in detail the sentiment of each sentence.
Identify opinions and facts
Distinguish between the expression of an objective fact or a subjective opinion.
Detection of irony
Identify those comments in which the opposite of what is said is expressed.Identify those comments in which the opposite of what is said is expressed.
Distinguish very positive and very negative opinions, as well as the absence of sentiment.
Agreement and disagreement
The detailed analysis allows to identify opposing opinions and contradictory or ambiguous messages.
What level of accuracy can the automatic sentiment analysis provide?
The first question that arises when talking about automatic sentiment analysis is: “What level of accuracy can be obtained?”. Actually, discussing “if accuracy is below XX%, the solution is unacceptable” is not a good idea: accuracy and coverage are not independent and usually it is advisable to reach a compromise between the two. What constitutes an acceptable performance in each case depends on the business problem as well. For example, an antiterrorism application might aim at 100% coverage, tolerating lower accuracy and false positives (that would be filtered by human reviewers). On the other hand, for other applications (e.g. brand perception in social media) might be acceptable to lose some cases –lower coverage– in exchange for greater accuracy.
Nevertheless, aspects such as volume and latency are equally or more important than the previous ones. If a human team can analyze hundreds of messages with 85% accuracy and a computer can process millions of them –in real time– with 75%, it is clear that machines are a definitely a valid option.
More info about Sentiment Analysis