Discovery Output Explanation

Discovery Mode Output

Semantria’s Discovery Mode provides you with a bird's eye view of your content after the sentiment has been analyzed. In this mode you can discover the top entities, themes, facets, topics, and overarching sentiment count of your group of documents. Semantria does the counting and rollup for you. This can be a good way to get on overview of what is in your data without having to put it into another tool to aggregate the output.

Discovery Mode output explanation

In Discovery mode, sentiment average is not supported. Instead, the positive, negative, and neutral counts available for facets are analogous to the positive/negative ratio; these show how many mentions of each type were in the text with respect to a certain facet.

Like in Detailed Mode, Discovery Analysis Output will have an analysis id, config_id, job_id, tag and status. The analysis will also return themes, entities and topics.

Discovery Mode Analysis returns the facets extracted from all documents in the batch of discovery analysis. Each facet has a label (the text of the facet), count (number of occurrences), negative_count (number of negative occurrences), netural_count, positive_count, and mentions.Each mention will have a label, an indicator, and negating_phrase. The API will also return attributes associated with the facet with accompanying labels, counts and mentions.

Users have the option for the Semantria API to return the original source document in addition to the processed results. This is useful for multi-level integrations. The option can be switched on and off on upon request.

This analysis can give you insight into problem areas within your business. With Discovery Mode you can see which of your hotel branches is underperforming or which competing brand is generating the most buzz on Twitter. Additionally, you can see the reasons behind the positive and negative feedback and quickly use that information to improve. You can also use your Discovery data to create charts and tables so that you can understand your data from a quick glance.

When sending a collection of texts (e.g. a set of 1,000 tweets) to Semantria, all content is analyzed simultaneously. All recurring mentions of an entity or theme are counted and available to you. In Discovery Mode our Excel Add-In will only display facets, attributes, and sentiment count due to Excel limitations, but Semantria is doing more work behind the curtain.

For example, when running Discovery Mode on a collection that contains the sentence “My waiter was rude!” Semantria will identify the word “waiter” as a facet and search for it throughout the rest of the texts. The attributes associated with “waiter” found within the collection are then consolidated so you will know how many people share the same feelings towards the waiter.