Behance is a social media platform owned by Adobe that allows artists to develop and share their artwork with other users. With more than 10 million users searching for inspiration, personalized recommendations play a pivotal role in the overall UX. The current recommendation algorithm at Behance requires substantial user activity to generate recommendations and surfaces artwork with higher likes more often. To make these recommendations more fine-tuned, we developed an algorithm using Cypher, that analyzes the activity of all related users & provides weight to project themes instead of likes. Our algorithm also reduced the recommendation generation time by 50%.