Automatic Hashtag Optimization for Instagram based on Text and Image analysis- BC-501

Desired discipline(s): Engineering - computer / electrical, Engineering, Computer science, Mathematical Sciences, Mathematics, Statistics / Actuarial sciences
Company: Anonymous
Project Length: 6 months to 1 year
Preferred start date: 07/06/2020
Language requirement: English
Location(s): Vancouver, BC, Canada
No. of positions: 1
Search across Mitacs’ international networks - check this box if you’d also like to receive profiles of researchers based outside of Canada: 

About the company: 

We are a media-tech company that helps content creators on various video platforms such as YouTube and Facebook with the creation, management, distribution, and monetization of content. We are providing these services through its innovative tech, leading services as well as distribution and monetization services. 


Please describe the project.: 

Hashtags are currently the main method of content discovery for Instagram, a digital media platform used by more than 1 billion users worldwide. However, the majority of users don't use hashtags properly (e.g., use wrong/spammy hashtags or don't use enough hashtags). 

This significantly impacts the discovery of related content for users and also impacts the discoverability of creators who create high-quality content but don't have enough time to generate the associated metadata properly.

In this research project, we want to propose methods based on text processing, natural language processing, machine learning and deep learning to automatically suggest proper hashtags for Instagram. This includes analyzing the quality of the existing hashtags and recommending how hashtags can be improved.


Required expertise/skills: 

  • Applicant must be pursuing or completing Masters, PhD, or Post-Doctorate in Electrical Engineering, Mathematics, Computer Science, Information Management or Statistics Degree
  • Good knowledge of text processing and NLP
  • Working knowledge of machine learning algorithm such as classification, and prediction
  • Know how to build deep learning models like RNN, CNN, DNN and other neural network models
  • Know how to design an experiment for testing the performance of a machine learning algorithm
  • Good working knowledge with Python
  • Familiarity with one of the data science platform such as Tensorflow, Theano or Pytorch is ideal
  • Ability to multi-task
  • Ability to work in a fast-paced environment
  • A pragmatic and solution-oriented mindset is absolutely necessary
  • Good attention to details
  • Critical Thinking