SAS® Sentiment Analysis
Automatically pinpoint sentiment from the Web and electronic documents
SAS Sentiment Analysis collects (i.e., crawls) digital content sources, including mainstream Web sites and social media outlets, as well as internal organizational text sources. It then uses powerful statistical techniques and linguistics rules to extract the sentiment expressed in these text collections – providing summaries, identifying trends and creating graphical reports that describe the expressed feelings of consumers, customers and competitors in real time.
Benefits
- Evaluate sentiment and monitor changes over time.
- Identify feedback sources to define new targets.
- Continuously improve customer experience and competitive position.
- Promote ongoing discovery with a closed-loop, integrated analysis environment.
Features
- Statistics and linguistics combined to provide more accurate sentiment analysis results
- Extended sentiment evaluation
- Context of features examined for accurate interpretations
- Dynamic sentiment analysis
- Easy-to-use interface for model development
- Interactive workbench for model refinement
- Updates on Web postings, reviews and opinions
- Multiple languages supported
How SAS® Is Different
- SAS Sentiment Analysis uses a hybrid approach based on statistical modeling and rule-based natural language processing (NLP) to automatically extract sentiments in real time or over a period of time from the Web or internal electronic document collections.
- Ongoing model refinement enables you to focus on current opinions, identify changes as they occur and flexibly augment evaluations with new information – constantly improving the effectiveness of your analysis and providing quantified insights on products, services and brands not previously available from the manual review of Web and other electronic-based content.
- Incorporating an extensive number of native languages and dialects, the software provides a detailed breakdown of text evaluations. Extrapolate information and create color-coded graphs to understand exactly what these commentaries mean in terms of overall expressed sentiment for your brand, products and services, as well as changes in these sentiments over time.
- As part of an integrated framework, SAS Sentiment Analysis can be combined with categorization, extraction and text mining models so you can extend existing taxonomy definitions to include the associated expressed sentiments. And as part of the SAS Business Analytics Framework, you can explore results in familiar reporting environments using SAS Business Intelligence and data visualization and discovery products.
Benefits
- Evaluate sentiment and monitor changes over time. The software automatically extracts sentiments in real time or over a period of time with a unique combination of statistical modeling and rule-based natural language processing techniques. Built-in reports show patterns and changing reactions.
- Identify feedback sources to define new targets. By actively monitoring internal collections (such as call centers and the Web) combined with social networking sites (like Twitter and Facebook), the software shows where you're being discussed and what is being said. It scores content retrieved from crawling, filtering out the most important concepts so you can pursue promising opportunities.
- Continuously improve customer experience and competitive position. The software searches for and evaluates internal and external content about your organization and competitors, identifying positive, negative, neutral and "no sentiment" texts quantifying perceptions in the market.
- Promote ongoing discovery with a closed-loop, integrated analysis environment. With ongoing evaluations, you can refine models and adjust classifications to reflect emerging topics and new terms relevant to your customers, organization or industry.
Features
- Statistics and linguistics combined to provide more accurate sentiment analysis results
-
- Provides a choice of approaches to sentiment analysis:
- Statistical modeling: Provides predefined default parameters – that can also be configured – to identify the document sentiment from text.
- Linguistic rules: Lets subject-matter experts define the elements to be examined for sentiment assessment.
- Hybrid approach: Provides the unique ability to use both statistical rigor and linguistic rules to define sentiment models driving more detailed sentiment evaluations.
- Ability to import and/or create concepts for evaluations.
- Provides a choice of approaches to sentiment analysis:
- Extended sentiment evaluation
-
- Specify as "unclassified" any terms in a taxonomy that are found in the text but are not identified as positive, negative or neutral. This capability provides two main benefits:
- Assists with model refinement.
- Helps refine activity by pointing out unemotional statements.
- Specify as "unclassified" any terms in a taxonomy that are found in the text but are not identified as positive, negative or neutral. This capability provides two main benefits:
- Context of features examined for accurate interpretations
-
- Supports complex linguistic rules for one or several matches of a term, regular expressions, part-of-speech tags, the distance or occurrence of concepts in relation to other words, and more.
- Includes prebuilt tasks to simplify linguistic pattern identification. It offers:
- Predicate rules to define semantic relationships between concepts.
- Operators to locate related information with greater precision, such as co-referencing.
- Identification of intermediate concepts that contain rules referenced by other concepts (shortens the rule-writing process).
- Case-insensitive matching, so you can match both uppercase and lowercase terms.
- Dynamic sentiment analysis
-
- Permits improvements and/or changes over time with multiple model generation within the same project, and the ability to edit and test model modifications.
- Allows subject matter experts to refine model performance with an easy-to-use point-and-click workbench.
- Monitoring of results over time will inform model analysis refinement, and comparisons to benchmark training sets can be established to allow for continuous improvement.
- Easy-to-use interface for model development
-
- A mechanism to directly upload sentiment analysis models to the server reduces manual model deployment.
- Keyboard shortcuts are available for interactivity, as well as enhanced search functionality assisting with model development activity.
- Project wizard allows you to configure your project while it is being defined.
- Panes in the interface simplify tasks and display more information, such as rule evaluations and search results.
- Interactive workbench for model refinement
-
- Graphics depicting sentiment are displayed to readily identify the resulting classification as positive, negative, neutral or unclassified.
- Point-and-click exploration of classified text, drilling to detail as desired.
- Enhanced report formatting improves results display.
- Ability to add new concepts/entities to capture desired topics.
- Word cloud report, based on defined concepts, automatically illustrates extracted noun phrases.
- Some workbench functionality is available through Web services APIs so documents can be programmatically added to different projects, exported, managed, searched, etc.
- Updates on Web postings, reviews and opinions
-
- High-performance, multithreaded crawler that can be deployed in a distributed mode to maximize processing and support extremely large-scale crawls for both internal file system and Internet crawls.
- Powerful linguistic technology is built in to extract URLs from Java scripts.
- Web crawls can be interrupted and resumed.
- Document processor makes it easy to parse, export and control processing and output.
- Duplications are automatically removed.
- Supports desired restrictions (e.g., to specific file formats or servers, restrict the area or specify search depth) on crawling to customize searches.
- Multiple languages supported
-
- Full suite of 27 languages (plus dialects) available.
- Supports Arabic, Chinese (both Simplified and Traditional), Czech, Danish, Dutch, English (US/UK), Finnish, French (French/Canadian), German (New/Old), Greek, Hebrew, Hungarian, Indonesian, Italian, Japanese, Korean, Norwegian (Nynorsk/Bokmål), Polish, Portuguese (Portugal/Brazil), Romanian, Russian, Slovak, Spanish (Spain/South America), Swedish, Thai, Turkish and Vietnamese.
Screenshots
Multilevel taxonomies classify sentiment detail to pinpoint issues.
Multilevel taxonomies classify sentiment detail to pinpoint issues at a deeper level, including document, concept, attributes and subattributes.
Graphics and user-friendly reports readily describe sentiment insights.
Graphics and user-friendly reports readily describe sentiment insights for exploring scored text and providing feedback to further refine models.
Visually compare different types of models, from statistical, rule-based or hybrid algorithms.
Use the point-and-click SAS Sentiment Analysis workbench to refine model classifications.
Search for particular keywords within defined date ranges, and even categories by classified sentiment.
Visually explore scored sentiment documents in charts – or, based on predefined categories, in phrase cloud format.
System Requirements
SAS Sentiment Analysis is a standalone product that requires no other SAS modules.
Client Environment
- Microsoft Windows (x86-32 and x64): Windows XP Professional, Windows 7**, Windows Server 2003 family, Windows Vista*, Microsoft Windows (x64): Windows XP Professional for x64, Windows Vista* for x64, Windows 7** for x64
- Microsoft Internet Explorer 8, Firefox, Chrome
Server Environment
- HP-UX Itanium: HP-UX 11iv3 (11.31)
- HP-UX PA-RISC: HP-UX 11iv3 (11.31)
- IBM AIX: 6.1 and 7.1 (x64) on POWER architectures
- Linux for x86 (x86-32): RHEL 5 and 6, SuSE SLES 10
- Linux for x64 (EM64T/AMD64): RHEL 5 and 6, SuSE SLES 10 and 11
- Microsoft Windows on x64 (EM64T/AMD64): Windows XP Professional for x64, Windows 7** for x64, Windows Server 2003 for x64, Windows Server 2008 for x64, Windows Vista* for x64
- Solaris on SPARC: Version 10
- Solaris on x64: Version 10
* NOTE: Windows Vista supported editions are Enterprise, Business and Ultimate.
** NOTE: Windows 7 supported editions are Professional, Enterprise and Ultimate.
Ready to learn more?
Call us at 1-800-727-0025 (US and Canada) or request more information.
