Geosocial networking app with street translator

We are working on a geosocial networking application that leverages geolocation and user time data to provide personalized recommendations for nearby locations, points of interest, events, and translation to needed language. The app aims to enhance user experiences by offering relevant suggestions tailored to their current location and time, fostering meaningful connections and engagement.

Project background

Geosocial networking apps are a relatively new type of social apps. The most popular players on the market are Yelp, Facebook Places, and Foursquare. These apps allow users to share their locations as well as find recommendations for locations, or ‘venues’.   

Sharing our location on online social networks has great advantages: it can help us find our way, pick restaurants and shops, and even locate nearby friends and other people within the selected radius. Our client wanted to create a unique geosocial networking solution powered by AI for the local market.  

The required recommendation system has to use:   

– Computer Vision to analyze images;

– NLP technology to analyze chat and image captions, and automatically pinpoint topics of interest, locations, dates and time for proper advice; 

– Recognition of voice commands in several languages; support of topic modeling of social messages, as well as syntactic text simplification of complex sentences in the information repository structured as a graph. 

  • Duration: May 2021 - Ongoing
  • Location: Seattle, WA, USA
  • Industry: Media & Entertainment
  • Services:
  • POC development, Web development

Business needs

Geosocial networking apps are a relatively new type of social apps. The most popular players on the market are Yelp, Facebook Places, and Foursquare. These apps allow users to share their locations as well as find recommendations for locations or ‘venues’.  

Our client wanted to create a unique geosocial networking solution powered by AI for the local market

– The client’s main idea was to change a commonly-used approach to social media posting and social networking apps, add voice and language recognition and create a unique recommendation system; 

– Our client was looking for a development team with experience in Machine Learning;   

– Our client wanted to start as fast as possible and create a working prototype of a recommendation model for his investors.  

Product features

  1. Calendar flow. The information in the app is organized according to the calendar flow, formed based on the time and location of the user
  2. Topic modeling. The content is broadcast from the location where the user is connected. It’s also broken down into thematic channels: news, food, housing, local stories, etc
  3. In-app chat. Users can communicate directly in the app, and attach photos and videos to their messages. Post commenting is also available
  4. Recommendation system. Based on information from the chats, images, and comments, the system offers users customized recommendations. For example, if a user is going to Kyiv for business, the system will offer relevant Kyiv-based locations so the user can plan his trip accordingly
  5. Bilingual recommendation system support. The system supports two languages, English and Vietnamese. Thanks to voice and language recognition technology, it’s now possible to avoid typing commands or requests
  6. Voice assistant. We used an out-of-the-box solution for the development of Voice assistant, Voice navigation, and Voice translation


Our team was in charge of the project, starting with the discovery phase and POC, and finishing with the development of the app prototype, adding new features and product support.

This social networking app is organized according to the principle of calendar flow. It is formed depending on the time and location of the app user. The content is broadcast from the place where the user is located and connected to the Internet.

Social communication is possible through the internal chat platform with the functionality to post photos and video files, and comment posts of other users.

To cope with a large amount of user data, our ML experts have built a knowledge graph of the social network. This custom database helps save and structure different facts given by users for further use in communication and recommendations.

The app automatically recognizes the event, date, time, and location of the user thanks to Named Entity Recognition (“What”, “Where”, “When”) or voice assistant powered by ChatGPT. Based on this information, the user receives a list of recommendations, answers to their questions, and even relevant translations of needed sights, and phrases.

Our technology stack

  • ReactJS
  • JS
  • Amazon AWS
  • CSS
  • HTML
  • Google Maps
  • Postman
  • Yarn
  • Babel
  • ES5
  • Redux-Saga
  • Jenkins
  • Python
  • PyTorch
  • Pandas
  • sklearn
  • Amazon S3
  • Amazon EC2
  • Amazon SQS
  • OpenNLP
  • Elasticsearch
  • Flask
  • Spacy
  • NLTK gensim

Client values

  1. Enhanced user engagement: Our customer expects generative AI to enhance user engagement in their geosocial app, resulting in a potential increase of up to 20% or more in active participants.
  2. Personalized marketing & promotions: By implementing generative AI, our customer anticipates delivering targeted marketing messages and promotions customized to user preferences, location, and behavior, leading to the potential growth of up to 8% in conversion rates and customer satisfaction.
  3. Efficient customer support: With generative AI automating customer support in the geosocial app, our customer aims to provide quick responses, answer FAQs, and guide users through issues, potentially reducing the support team workload and improving response times by up to 5%.
  4. Competitive advantage: By integrating generative AI like ChatGPT, our customer seeks to gain a competitive edge over rivals by offering personalized and engaging experiences, potentially leading to an improvement in retention by up to 6% or more.

Employee testimonial

Olha Kanishcheva Leading NLP Software Engineer, Data Scientist

The geosocial networking project is very interesting and technically challenging, and that’s the greatest appeal of it! We have tested a lot of models and technologies to solve certain problems. The most difficult part of the project, probably, was that at the start of the project, we did not have enough real data. The most memorable thing for me was the creation of a knowledge graph for the social network. The task turned out to be very multifaceted and included many other subtasks.

Let’s bring your idea to
life together!

    Successfully applied!