Data Collection
Sentiment Analysis and Classification
Influencer Detection
Data Representation


Somatech develops a customizable solution that rapidly capitalizes on the vast amount of underutilized (textual and structured) CRM data. The solution accesses and analyses the invaluable information generated by customers through emails, social media and call center records so providers can proactively improve customer satisfaction and reduce problems.

  • Expertise with Data Mining and Machine Learning
  • Easily scalable and configurable
  • Participated MIT Global Founders' Skills Accelerator (MIT GFSA) 2013 as the only Turkish team
  • Technically validated by SAP Startup Focus Program
  • SAP HANA integration for scalable text analysis


    The Power of Deep Learning!

    Deep learning is the fastest-growing field in artificial intelligence, helping computers make sense of infinite amounts of data in the form of images, sound, and text. Using multiple levels of neural networks, computers now have the capacity to see, learn, and react to complex situations as well or better than humans. This is leading to a profoundly different way of thinking about your data, your technology, and the products and services you deliver.

    What Does Somatech Offer?

    Somatech solutions can help IT and business users to collaborate, analyze, and exploit data by maximizing the value that they achieve with record-breaking accuracies with Deep Learning.

    Data Modelling
    Sentiment Analysis
    Customer Segmentation
    Data Monitoring

    Information Categorization

    Our summarization engine can analyse a list of reviews about a particular brand or product and categorize them according to different aspects. The grouped reviews would be easy to go through and analyze.

    Information Summarization

    In addition to aspect-based categorization, our summarization engine can be used to group reviews according to sentiment and informativeness; and to remove short or slang reviews while summarizing their sentiment statistically.

    Sentiment Analysis

    Our sentiment analysis engine can analyse a given natural language text and extract the sentiment (negative or positive) in it. It can thus be used for categorizing and quantifying comments in social media. Our technologies are developed both for Turkish and English.