Text Analytics

Build advanced natural language capability over raw text, and offer following functionalities:

1. Sentiment analysis

Find out what customers think of your brand or topic by analyzing raw text for clues about positive or negative sentiment

2. Key phrase extraction

Extract key phrases to quickly identify the main points. For example, for the input text “The food was delicious and there were wonderful staff”, the solution returns the main talking points: “food” and “wonderful staff”.

3. Language detection

Detect text language and report a single language code for every document submitted on the request in a wide range of languages, variants, dialects, and some regional/cultural languages. The language code is paired with a score indicating the strength of the score.

4. Named entity recognition

Identify and categorize entities in the text as people, places, organizations, date/time, quantities, percentages, currencies etc. Well-known entities are also recognized and linked to more information on the web.

Our Approach

We build a uniform data storage layer that feeds the NLP models to run text analytics scenarios. The outputs can be summarized to derive actionable insights from the reporting layer

Text Analytics Approach

Our NLP based Text Analytics technique uses following techniques-

  1. Tokenizer. Splitting the text into words or phrases.
  2. Stemming and lemmatization. Normalizing words so that different forms map to the canonical word with the same meaning. For example, “running” and “ran” map to “run.”
  3. Entity extraction. Identifying subjects in the text.
  4. Part of speech detection. Identifying text as a verb, noun, participle, verb phrase, and so on.
  5. Sentence boundary detection. Detecting complete sentences within paragraphs of text.

Classify a broad range of entities from the text data, such as people, places, organizations, date/time, and percentages, using named entity recognition. Detect and extract more than 100 types of personally identifiable information (PII) and more than 80 types of protected health information (PHI) in documents.

Quickly evaluate and identify the main points in unstructured text. Get a list of relevant phrases that best describe the subject of each record using key phrase extraction. Easily pull and organize information to make sense of important topics and trends.

Detect positive and negative sentiment in social media, customer reviews, and other sources to get a pulse of your brand.

Run Text Analytics wherever your data resides. Build applications that are optimized for both robust cloud capabilities and edge locality using containers.

Use Cases

Measure Voice of Customer (VoC) (Retail, e-Commerce)

Efficient capture and analysis of customer satisfaction and opinion pertaining to their experience with your business.

Analyze Customer Sentiment (Retail, Banking)

Find out what your customers think of your brand or topic by analyzing raw text for scoring around positive, neutral or negative sentiment with a score between 0 and 1 for each document, where 1 is the most positive.

Optimized Customer Care- Analyze recorded inbound customer calls (Engineering)

Optimize your Contact Centre operations by in-depth analysis of customer interactions across multiple touch points .

Got a Project? Let's Talk

Whether you are planning or are already in the midst of your transformation journey,our experts can help you accelerate your transformation initiatives.