NEW web technologies and especially social networks enable users to share and discuss common interests and provide infrastructures for integrating various user experiences: synchronous and asynchronous communication, game-playing, sharing links and files. Social network and social interaction using mobile and cloud platforms capture vast amounts of data that can be mined to discover implicit knowledge, common beliefs, preferences, and experiences, that could potentially empower users to learn from each other and together. The trend of using social networks and social media to deliver and exchange knowledge could bring a new era of teaching and learning. Unlike a traditional e-leaning paradigm with pre-defined curriculum and standard textbooks, social knowledge could be aggregated on demand, just in time, and in context of engaging challenges from social networks, making learning more exciting, social and, game-like experience. Therefore, the use of social computing techniques and social knowledge for e-learning is being actively investigated. This special section of the IEEE Transactions on Learning Technologies (TLT) focuses on technologies and experiences of using social networks in e-learning. In addition to open submission, the best papers from top international conferences in related areas were invited. Thirty-one submissions were received. Of these, twenty-two were in scope and went through several rounds of peer-review. Finally, five papers were accepted (21 percent). The scope of the submissions shows the vigor and diversity of research that is going on in the area at the moment. One third of the submissions focused on recommending either team members for collaboration (three submissions) or content (three submissions) using social interactions data in online social learning environments. Since the methodology in the area of recommender systems is fairly mature, with clear standards for evaluation, half of these submissions ended upmeeting the standard for acceptance. Four submissions focused on mining patterns from learner actions and social media data. The area of educational data mining is also well established (with its own conference and clear standards for evaluation) and the highest proportion of accepted papers (three out of four) came from this group. Three submissions investigated possibilities for integrating learning experience in specific online social networks, applications or massive open online courses (MOOCs). Unfortunately, mostly due to the difficulty of carrying out evaluations in open commercial systems, the papers in this group could not demonstrate convincing results. Two further submissions addressed user motivation in social learning environments through gamification or self-assessment. None of these papers was able to meet the standard for publication. The remaining submissions applied techniques specific for social computing (e.g. tagging, social virtual worlds, trust and reputation, bee colony optimization algorithms) in the context of (collaborative) learning environments and investigated pedagogical issues and user experience. All of these papers, even though not accepted in the special section, showed that interesting and original research is going on in the area, which will hopefully lead to significant and influential results in the future. Five papers comprise the special section. Two of them focus on recommendingmembers for a team or recommending content in social learning networks and environments. “Facilitating Enhanced Social Collaboration in Mobile Cloud-Based Learning: A Teamwork as a Service (TaaS) Approach” by Geng Sun and Jun Shen describes a collaborative platform in Moodle that allows the configuration of jigsaw classroom collaboration between students on both desktop and mobile devices. Kolb’s experiencial learning cycle and learning styles is used by a service, implemented in a cloud-based infrastructure, to group learners in teams based on their social features. A genetic algorithm is used to discover successful team task allocations. A simulationbased evaluation shows that the genetic algorithm delivers good team formation and task allocations. The user evaluation is based on three case studies in several university-level courses. The results show improvement in the collaborative learning experience of students and a high evaluation of the tool by the teachers. “A M-Learning Content Recommendation Service by Exploiting Mobile Social Interactions” by Han-Chieh Chao, Chin-Feng Lai, Shih-Yeh Chen, and Yueh-Min Huang analyzes a mobile learning community, and develops a timevarying recommendation strategy based on individualized responding messages. The results show that learners are more willing to continue their learning process based on the recommendation, which can also be used to attract additional learners. The experiments use 17 primary school students as the test subjects. The findings show that the T.K. Shih is with the National Central University, Taiwan. Jhongda Rd., Jhongli City, Taoyuan County 32001, Taiwan, R.O.C. E-mail: email@example.com. J. Vassileva is with the Department of Computer Science, University of Saskatchewan, 176 Thorvaldson Bldg., 110 Science Place, Saskatoon, SK S7N5C9, Canada. E-mail: firstname.lastname@example.org.