Thank you!
We will contact you shortly
Solution for Media monitoring. Media intelligence for PR, business, market research, reputation management, etc.
Problem
Solution description & benefits
The Harvester can select information related only to a certain person, company or targeted topic among huge amount of data noise generated every minute by various online media and social networks.
It can also be used for processing data extracted by special apps – social media crawlers (e.g. CrowdTangle, TwitterDeck, Semantrum, etc.) used for surfing along social networks and other media. The Harvester can boost processing of large data sets, filter out unnecessary data, categorize the results by topic, keywords and persons. The crawlers normally segregates and downloads searched data in text format files (.xls, .xlsx, .txt, .doc, .docx, .svd).
Users can add their own sources for monitoring
YouTube channels, online news platforms, etc).
The Harvester provides 24/7 monitoring of multiple media resources in a row
and receives data with the moment something specific is said or a certain person or object appears on screen.
All videos are checked for the presence of the target person
If the files meet the specified criteria, they are submitted for further processing and analysis.
All audio is analyzed for the presence of a specific speaker
If there is a speech of a particular person they are submitted for further processing and analysis
Also all audio files with recorded human speech could be converted into text
All text files could be searched for critical words specified by the operator
The more different combinations of such words a file contains, the higher its rank
Moreover, all text files could be processed by automatic Sentiment analysis, Summarization & Categorization as per predefined topics
The User receives a categorized database with only relevant information on the specific person, company or topic
Then he can cross-check the information from the text, audio and video files
Essential to note that the Users can adjust automated alerts and filterings
for avoiding irrelevant mentions
The Harvester allows working with different languages at the same time and translating any audio speech and text content into the other languages
Key Technologies
Data types
Video & Images
● recognition of a person on the face (identification/verification) and analysis of portrait characteristics● people search● objects search and detection
Audio
● recognition of a person by voice (identification/verification)● speech transcription (audio to text conversion)● retraining of language models for transcription● speaker language identification in audio● determining the gender of a person in audio
Text
● language identification● translation of text documents● keyword spotting● sentiment analysis● text document summarization● named entity recognition● text documents● categorization by predefined topics
To trust us, try it out with your own data
Need few more text