The OpenText Sentiment Analysis module is a specialised classification engine used to identify and evaluate subjective patterns and expressions of sentiment within textual content. The analysis is performed at the topic, sentence, and document level and is configured to recognise whether portions of text are factual or subjective and, in the latter case, if the opinion expressed within these pieces of content are positive, negative, mixed, or neutral

Type of content: Assets
Type of asset:
Application / Tool
Big data potential
Phase in the policy cycle:
Policy Design and Analysis
Open license availability
SWOT Analysis for
Helpful Harmful
Strengths• Automated extraction of sentiment on topics, sentences and documents.
• Full language support of English, French, Spanish, German and Portuguese.
• Specific configuration for user-generated content out of the box.
• Flexible infrastructure for minimal time-to-business deployment.
• On-premise installation or as a Cloud service.
• Simple XML output.
• Easy customization for specific requirements.
• API library of sentiment-centric and data visualization widgets.
• Create custom queries: Tap into the Content Analytics repository and select topics to create rich queries. Add sources of content; track these queries through time.
• Interactive data visualizations: Use trends and topic maps to navigate through the data; add filters, refine your searches, and get to the heart of what you really want to know.
• Create alerts: Receive notices when a topic of interest pops up in the conversion.
• Get recommendations: Let the engine recommend influencers that you should contact, communities that you should join or issues that you should address.
Weaknesses• Low ease of use
• No open license availability
Opportunities• Brand monitoring: Monitor the sentiment around a brand and its products.
• Campaign monitoring: Create and follow the development of a marketing campaign as it unfolds within internal and external content channels.
• Competitive intelligence: Follow competitors and assess the perception of customers around their activities.
• Identifying influencers: Find out who is talking about your brand across several channels.
Threats• The initial coding of texts is crucial in establishing the categories to be analysed: if the coding is inaccurate then the findings are invalid
• Misinterpretation: the researcher may ignore the context that the words are used in
• It’s imperative to have a sufficiently sophisticated and rigorous enough approach that relevant context can be taken into account

Open data - Download the Knowledge base

You are free to download the data of this Knowledge base.

To do this you must be an authenticated user: log in or sign in now.

All the data are licensed as Creative Common CC-BY 4.0.