Category Archives: topic extraction

Service Marathon

DATA ANALYSIS AND CLIENT EXPERIENCE MANAGEMENT

This past Saturday June 22, our CEO has taken part in Service Marathon held In Kyiv, Ukraine — remotely from New York City.

These were the main topics of the discussion:

• How and to what extent should client behavior be analyzed, what to do with large data sets (big data)?
• Where and how to collect data, interpret and use the results of the analysis? What metrics should I use?
• Is it possible based on the analysis of data to improve the service policy of the company and improve customer service?

In particular, Dmitry has paid a lot of attention to methods of text analysis for understanding customer feedback, improving services and internal business polices to achieve a better and smoother client-centric service.

As a business dealing with text data generated by your customers or target audiences, you want to:

  • Evaluate emotion / sentiment of your clients with Fuxi API (for Chinese) and RSA API (for Russian).
  • Extract main topics of discussion to stay on top of what’s important right now using DocTop API (supports a multitude of languages).
  • Not enough text facets? Order a comprehensive text understanding service from our specialists and improve your business processes.

New DocTop API: identify meaningful topics in documents in 8 languages

We are excited to share the news: we have just launched new DocTop API for identifying and extracting meaningful topics from documents in English, French, German, Dutch, Italian, Portuguese, Greek and Spanish.

You can send multiple documents for analysis in a single JSON request. First 10 documents will be analyzed.

Curiosity rover exploring topics in text data

When do you want to extract topics from unstructured text? Here are a few reasons:

  • Find out what are the top standing out topics that your documents are talking about.
  • Identify trends. For this, you can systematically collect topics for new documents and compare with volumes of same topics in the past.
  • Tag documents with topics to group them.
  • Allow searching within topics of interest to get focused search results.
  • Track topics to make a sense of the textual data being produced and become more data driven.
  • Correlate topics with other facets of your data, like geography, user age brackets, gender etc.

Here is an example of how to use the API for English:

[
	{
		"article_id": 1,
		"text": "San Francisco considers banning sidewalk delivery robots"
        }	
]

In response to the request above you’ll get an array of identified topics:

[
  {
    "article_id":1,
    "topics":[
         "sidewalk delivery robots"
         "san francisco"
    ]
  }
]

And here is the request/response pair for a text in Spanish:

[
	{
		"article_id": 1,
		"text": "Apple está buscando comprar una startup del Reino Unido por mil millones de dólares"
    }	
]
[
  {
    "article_id":1,
    "topics":[
       "reino unido"
       "millones"
       "startup"
       "dólares"
       "apple"
    ]
  }
]

Subscribe to the DocTop API today and test it out on free 100 texts in any supported language!