In recent years, interest in heterogeneous information network analysis (HINA) has led to advances in information propagation and trust (news propagation, fake news, political influence, and viral memetics), crowdsourcing and marketing, bot detection, community modeling, analysis of citation networks, recommender systems, and other areas of social informatics. Four previous workshops on HINA have focused on transdisciplinary advances in network modeling, incorporating representation of heterogeneity, path analysis, frequent subgraph mining, community detection, and using learning and inference in graphical models of probability to capture important aspects of heterogeneous information networks.
Active research areas that are relevant to heterogeneous information networks include:

• Convergence of data science and social informatics: KDD/ICDM, ICWSM, SocInfo-relevant topics
• Social good, social influence, detection of malign uses of information networks: fake news, bots
• Metapath-based similarity measures and relationship extraction
• Models of information propagation across domains and social media
• Progressing beyond APA and APVPA models of citation networks
• Social sentiment analysis and topic models in HINA
• Community detection and formation modeling
• Applications to modeling of weblogs, social media, social networks, and the semantic web
• Trust networks, information sharing, and limitations of existing models
• Learning to rank in HINA
• Modeling of link types and relationship strength