Need Help?

Analytics: Key Terms

Last Updated: May 19, 2017

Here are the definitions of key terms in Luminoso Analytics.

Association Score: An association score measures how strongly related two concepts or groups of concepts are. Association scores range on scale from -1.00 to 1.00. These are upper and lower limits that represent the weakest and the strongest possible relationships: a score of 1.00 represents the relationship between a concept and itself, while a score of -1.00 is the relationship between a concept and the most unrelated other concept within the same data set. See the article "What are Association Scores? What do they mean?" for more information.

Concept: A concept is a term or phrase that appears in your data set. It can be a single word or term, such as "amazing" or "smelly," or a phrase (colocation), such as "love my Kindle" or "not fast enough.”

Conceptual Match: A conceptual match is a match between a term or phrase you searched for or selected in the Dynamic Concept Cloud, and another term/concept that it is closely related to, though not necessarily exactly, the same. For instance, if you are analyzing the concept "delicious," conceptual matches might include concepts like "yummy" and "tasty" in addition to "delicious.”

Document: A document is a row in the .csv file that you upload to Analytics. Also referred to as a "verbatim."

Exact Match: An exact match is a match between the concept you've searched for/are analyzing and any concept that is exactly the same. For instance, if you are analyzing the concept "delicious," searching for an exact match would return documents that include the concept "delicious," but not closely related concepts like "yummy" or "tasty.” Different iterations of the same word are also considered exact matches (e.g., disappointed, disappointing, disappointment).

Project: The basic unit of analysis in Luminoso Analytics. A project is built out of a set of documents; the documents and metrics in one project have no influence on or connection to other projects.

Subset: A subset is a group or category of data within your overall dataset. For example, your data set might contain metadata such as the number of stars given in a product review or the gender of the reviewer. This metadata can be used to create subsets and analyze trends across the different groupings within the data set.

Subset Title: A subset title is a general way to describe the type of metadata within a subset. For example, "number of stars" and "gender" are subset titles, which describe the type of information being used in each unique subset.

Subset: A specific category of data within the overall dataset. For example, "4 stars" (rating) would be one unique subset under "number of stars," and "female" would be another unique subset under "gender." These subsets must be set up in the data prior to uploading into a project.

Topic: A topic is a concept or group of 3-4 concepts that has been saved for analysis. A topic can be a single concept, such as "amazing" or it can include multiple closely related concepts. One common example is a "Positive Sentiment" topic. This topic might include such related concepts as, "love," "recommend," and "great." We recommend that topics include no more than four concepts, and that the concepts be closely or conceptually related for maximum analytical effectiveness. See also: Difference Topic and Zero Topic.

Verbatim: See “Document." Source documents contain the natural-language text from product reviews, chat logs, customer service call transcriptions, open-ended survey responses, support emails, etc.


More Support
seconds ago
a minute ago
minutes ago
an hour ago
hours ago
a day ago
days ago
Invalid characters found