{"id":19856,"date":"2020-01-28T14:34:42","date_gmt":"2020-01-28T14:34:42","guid":{"rendered":"https:\/\/www.arimetrics.com\/glosario-digital\/sentiment-analysis"},"modified":"2026-09-15T07:57:53","modified_gmt":"2026-09-15T07:57:53","slug":"sentiment-analysis","status":"publish","type":"encyclopedia","link":"https:\/\/www.arimetrics.com\/en\/digital-glossary\/sentiment-analysis","title":{"rendered":"Sentiment Analysis"},"content":{"rendered":"

\"SentimentDefinition:<\/strong><\/p>\n

Sentiment analysis<\/strong>, also known as opinion mining, is a set of methods that identifies and classifies opinions, attitudes or evaluations expressed in text. It can be applied to reviews, surveys, customer service messages, social posts and other written sources.<\/p>\n

Its output commonly indicates positive, negative or neutral polarity, although it may also locate opinions about specific aspects or estimate emotions and degrees of intensity. These tasks are not equivalent<\/strong> and must be defined before the data is interpreted.<\/p>\n

The analysis may be performed manually or through rules, statistical models and artificial intelligence<\/a> techniques. Automated classification represents an estimate<\/strong>, not an unambiguous reading of each person’s intention.<\/p>\n\n

How sentiment analysis works<\/h2>\n

The process begins by defining the question, source and unit to be classified. Analysing a complete document, a sentence or a specific aspect<\/strong>, such as price, delivery or support, does not produce the same result.<\/p>\n

A common workflow includes these five stages:<\/strong><\/p>\n

    \n
  1. Collection:<\/strong> select relevant texts and retain the necessary information about language, date, channel and context.<\/li>\n
  2. Preparation:<\/strong> correct formats, detect the language and handle duplicates, noise or fragments that cannot be interpreted.<\/li>\n
  3. Representation:<\/strong> transform the text into features that a rule-based or machine learning<\/a> system can process.<\/li>\n
  4. Classification:<\/strong> assign a category, score or multiple labels according to the defined objective.<\/li>\n
  5. Evaluation:<\/strong> compare a sample against human annotations and review errors, coverage and changes in performance.<\/li>\n<\/ol>\n

    Lexicon-based approaches associate words or expressions with a predefined orientation. Trained models learn patterns from labelled examples. Hybrid systems can combine both methods<\/strong> and add rules specific to a language or field.<\/p>\n

    Aspect-based analysis attempts to link an evaluation to the element it concerns. A review may be positive about a camera and negative about its weight; a single label for the entire text would hide that difference<\/strong>.<\/p>\n

    Applications of sentiment analysis<\/h2>\n

    The technique can summarise large sets of opinions and locate cases that require review. Its common applications include these five:<\/strong><\/p>\n