Sentiment analysis, which is sometimes referred to as "opinion mining", is a technique to determine whether the context of a text piece is positive, negative or neutral. It is a branch of AI and natural language processing (NLP)that has proven beneficial for businesses when monitoring customers' or staff's feedback.
Nowadays, we can see sentiment analysis results on product reviews too; amazing information for both producers and shoppers.
Why sentiment analysis?
Sentiment analysis focuses on the polarity of a text (positive, negative, neutral) and has been proven helpful for businesses in detecting sentiment in the received feedback which leads to a better understanding of needs and goals.
The three most common types of sentiment analysis are
- Binary: positive and negative tagging
- Tertiary: positive, neutral and negative tagging
- Graded: normally rates of 5, such as [very positive, positive, neutral, negative, very negative]
We use neural network models for sentiment analysis. These networks are trained on large datasets and vastly tested on in-domain and out-of-domain testsets.
We have provided you with a no-code platform in which you can apply state of the art neural models to your data and benefit from this analysis
Not only you can access overall sentiment statistics in your dataset but also when combined with filtering you can analyse "sentiment over time" and sentiment in different categories (e.g. in a department, or a project).
Below you can see two samples of sentiment analysis on staff feedback data on our dashboard. The first one is the overall view on the whole dataset.
And the second image shows the analysis in one cluster in a mostly positive subset of data:
Another closely related NLP task is emotion analysis.
Updated about 1 month ago