Loneliness is a global issue which is particularly prevalent among college students, where it poses risks to mental health and academic success. Chronic loneliness can manifest in two primary forms: social loneliness, which is defined by a lack of belonging or a social network, and emotional loneliness, which comes from the absence of deep, meaningful connections. Differentiating between these forms is crucial for designing personalized and targeted interventions. Passive sensing technology offers a promising, unobtrusive approach to detecting loneliness by using behavioural data collected from smartphones and wearables. This study investigates behavioural patterns associated with social and emotional loneliness using passively sensed data from a student population. Our objectives were to (1) identify behavioural patterns linked to social and emotional loneliness, (2) evaluate the predictive power of these patterns for classifying loneliness types, and (3) determine the most significant digital markers used by machine learning models in loneliness prediction. Using statistical analysis, machine learning, and SHAP-based feature importance methods, we identified significant differences in behaviours between socially and Emotionally Lonely students. Specifically, there were distinct differences in phone use and location-based features. Our machine learning analysis shows a strong ability to classify types of loneliness accurately. The XGBoost model achieved the highest accuracy (78.48%) in predicting loneliness. Feature importance analysis found the critical role of phone usage and location-based features in distinguishing between social and emotional loneliness.