The School of Information Sciences has a long tradition of excellent research programs and laboratories. As part of a major research university, the school is dedicated to expanding the body of knowledge and creating the next generation of information technologies through its research.
| Adaptive Web Systems | Big Data | Cloud Computing | Data Visualization |
Human Robot Interaction | Intelligent Web Information Access |
iSchool & ULS Digital Scholarship Observatory Research Group | Learning Technology |
Machine Learning | Network Science | Spatial Informatics | Security |
Social Computing | Wireless Information Systems | Decision-theoretic Decision Support Systems
Adaptive Web Systems has grown from a narrow research field to a important part of our lives. We watch movies follow suggestions from Netflix, enjoy personalized music streams from Pandora and Last.FM, receive personalized search results from Google, and get link recommendations in LinkedIn. Faculty and students at our school investigate a broad range of user-adaptive systems: adaptive hypermedia, adaptive search, recommender systems and adaptive educational systems presenting their work at UMAP, AI-Ed, ITS, EDM, RecSys, WWW, IUI, SIGIR, Hypertext, and other top conferences.
Our papers brought home an extensive best paper award collection including four most prestigious awards in the area of personalization -- James Chen best student paper awards. The majority of research projects on this topic is now focused on personalization based on social data, i.e., information directly or indirectly left by the large community of users. Among the topics investigated at our School are social navigation in hyperspace, recommendations based on social tags and social links, and open social student modeling e-learning systems.
The new effort on Big Data Analytics couples several faculty including:
- Peter Brusilovsky - adaptive Web systems, social Web, adaptive hypermedia, etc.,
- Marek Druzdzel - decision support systems, strategic planning, decision making under uncertainty, decision-theoretic methods in intelligent information systems,
- Stephen Griffin - interdisciplinary scholarly communication, cultural heritage informatics and data-intensive scholarship,
- Daqing He - information retrieval and interactive retrieval-system design, user-modeling and adaptive Web-search system design and analysis, computational-linguistics and natural-language processing,
- Hassan Karimi - mobile computing, navigation, location-based services, geoinformatics, location-aware social networking, geospatial information systems, computational geometry, grid/distributed/parallel computing, and spatial databases,
- Yu-Ru Lin - human and social dynamics, computational approaches for mining and visualizing large-scale, time-varying, heterogeneous, multi-relational, and semi-structured data,
- Konstantinos Pelechrinis - wireless network systems, wireless networks security, trustworthy network operations, mathematical foundations of communications networks, and graph mining of the Internet,
- Vladimir Zadorozhny - networked information systems, complex adaptive systems, heterogeneous data fusion, wireless and sensor data management, query optimization in distributed environments, scalable architectures for wide-area environments with heterogeneous information servers.
- Balaji Palanisamy - Cloud Computing systems, MapReduce/Hadoop-based Big Data computing, Datacenter Performance optimization and cost-effective resource management, performance optimization for NoSQL/key-value stores, privacy and security conscious Big Data processing in Clouds, distributed storage systems for low latency cloud and Big Data applications.
In recent years, cloud computing and its pay-as-you-go cost structure have enabled infrastructure providers, platform providers and application service providers to offer computing services on demand and pay-per-use just like how we use utility today. This growing trend in cloud computing, combined with the demands for Big Data, is driving the rapid evolution of datacenter technologies towards more cost-effective, consumer-driven and technology solutions. Faculty members in the School who lead research in this area include Drs. Balaji Palanisamy, Vladimir Zadorozhny and Hassan Karimi. Example topics explored include performance optimization techniques for MapReduce/Hadoop-based Big Data processing, cost-effective datacenter resource management schemes and scalable parallel processing and distributed computing techniques for geospatial data, large scale information integration and data fusion.
Faculty contact: Dr. Balaji Palanisamy
Data visualization has been increasingly important in this "big data" world. With the explosion of different types of data generated from multiple sources, ranging from research groups, government agencies to participatory sensing data collected through social media and mobile devices, it is important to provide intelligent interface for all stakeholders in order to support actionable information seeking, particularly for supporting collective sense-making, situational awareness, and dissemination of credible crisis-relevant information. In our school, we have worked on new visualization techniques that enable people to synthesize information and derive insight from massive, dynamic, multi-sourced, multi-faced, interrelated and sometimes conflicting data, and provide timely assessment for making decisions. Our work has been featured in the most prestigious visualization venues including TVCG, InfoVis and VAST.
Human Robot Interaction (HRI) is becoming increasingly important as Moore's Law has spread from memory and processors to sensors and the internet of things. With accurate and inexpensive depth sensing provided by laser range finders and more recently rgb-d cameras such as the Kinect it is now possible to integrate robots into human environments without the danger and expense of only a few years ago. Whether in commercial applications where the Baxter "pick and place" robot can automate light assembly tasks for less than the cost of a family sedan to the ubiquity of drones in military and now civilian applications, robots are extending the computing revolution into the physical world. Our school has been at the forefront of this emerging field for the past 15 years with major grants from NSF, AFOSR, AFRL, ONR, and NIST.
Intelligent Web Information Access examines various sub-topics areas of information access and retrieval to web information, which include adaptive and interactive information retrieval, information access using mobile devices, and collaborative and social information access.
Digital Scholarship has been defined as “the use of digital evidence and method, digital authoring, digital publishing, digital curation and preservation, and digital use and reuse of scholarship” (Rumsey, 2011). In summer 2014, the iSchool and the University Library System (ULS) formed a partnership to build support for digital scholarship at the University of Pittsburgh and respond to faculty and students’ needs and interests in this area.
The ULS has created a pilot lab and consultation space for digital scholarship creation and support in Hillman Library, which is staffed by ULS librarians and post-doctoral researchers holding joint appointments with the iSchool and ULS. The iSchool is leading a research initiative focused around the partnership and the space managed by ULS. The new group, called the iSchool & ULS Digital Scholarship Observatory, brings together iSchool faculty and students with ULS practitioners and others with research interests in digital scholarship.
The iSchool & ULS Digital Scholarship Observatory aims to define and prioritize a research agenda in digital scholarship, with a focus on the support and service needs of faculty and students, and existing and potential contributions of academic libraries in this area. The advocacy mission of the partnership is reflected in the participatory form of research favored by the group, which aims to engage stakeholders in collaborative inquiry with an action agenda leading to practical outcomes. Another key goal is to advance the academic library profession by building a practitioner research community and encouraging research collaborations among LIS researchers, students, and practitioners.
Learning Technology has been an important research area for many years. The growth of Web-based education and more recently the popularity of MOOC has rapidly increase the demand for faculty and industry experts in this field. Learning technology research at Teaching and Learnng Research Lab (TALER) at our School is mostly focused on advanced Web-based technologies for teaching information science subjects. With the support of several NSF grants to we developed and explored several innovative interactive systems to teach Databases, C programming, and Java programming. These systems are used at Pitt and many other universities every semester. The current priority topic of our learning technology research is learning analytics, educational data mining, and data driven e-learning personalization: i.e., personalization based on mining large volume of data left by past students of e-learning systems.
Machine learning techniques are a leading component of the data mining toolbox. New approaches to both unsupervised and supervised learning have been introduced, and are already being incorporated into applications in information retrieval, natural language processing, and object recognition. Some of the recent topics explored at our school include ontology mapping and multi-modal learning.
A large number of information-related phenomena can be studied through the metaphor of networks. The advancement of interconnected information and communication technologies has made networks one of the dominant ways of analyzing the use and flow of information among individuals, institutions, and societies. Several faculty members at our school have led research in this area, including Drs. Yu-Ru Lin and Konstantinos Pelechrinis. They explore novel network metrics, models and mining techniques and apply network science on a variety of applications such as social network analysis, urban informatics as well as communication networks.
Faculty Contact: Dr. Konstantinos Pelechrinis.
The Spatial Information Research Group at the University of Pittsburgh is dedicated to the study and use of spatial information across a wide variety of contexts. Spatial information theory forms the underpinnings to developments in geographic information systems, navigation and information visualization. Specific research interests of the group include wayfinding and navigational aids, formal approaches to spatial reasoning, empirical studies on human spatial cognition, and the use of spatial metaphors in non-spatial contexts.
Cutting-edge research in the area of information security and privacy research is being conducted at School's Laboratory of Education on Security Assured Information System (LERSAIS), which has been designated as a Center of Academic Excellence in Information Assurance Education and Research (CAE & CAE-R) jointly by the US NSA and DHS. The recent survey ranks our Information Security and Privacy program 7th in the nation. The research carried out at LERSAIS focus on security and privacy solutions for emerging large scale distributed environments such as Cloud Computing, Social Networks, Smart Grids, Mobile/Wireless infrastructures, and Healthcare systems. Theoretical and practical solutions to trust, security and privacy challenges have been the focus of LERSAIS faculty members, who have been supported by funding from federal and industry sources. As part of SIS, LERSAIS is in the midst of a highly interdisciplinary environment, positioning itself as an ideal place to tackle multi-faced problems in the area of security, privacy and trust.
The research in the area of Social Computing explores the role of information technologies in understanding of social online systems such as Wikipedia, Question/Answer sites, and Social Networking. Several faculty at the School of Information Sciences lead research in this area, including Drs. Rosta Farzan, Yu-Ru Lin, Daqing He, and Peter Brusilovsky. They explore qualitative, quantitative, and computational methods in understanding how social information systems are used and impact the society and how these systems can be designed more effectively to address information needs of individuals, communities, and the society.
Faculty Contact: Dr. Rosta Farzan.
Wireless systems have become a vital infrastructure in today's society. The Wireless Information Systems group comprising of several faculty members - Drs. Ackers, Krishnamurthy, Pelechrinis, Tipper, and Weiss have exciting areas of research that include innovative ways of spectrum utilization and management, resilience of wireless networks, human use of mobile information and security of wireless information systems. The faculty have a long track record of federal research funding from the National Science Foundation, Army Research Labs, and the National Institute of Standards and Technology supporting the research.
Faculty Contact: Dr. Prashant Krishnamurthy.
Data collection and analysis is merely the first step toward exploiting information. The most important step is making decisions based on the information gained. The focus of Decision Systems Laboratory is building decision support systems that are based on sound principles of probability theory, statistics, and econometrics. Building such systems rests usually on a careful combination of expert knowledge and data analytics. Decision-theoretic systems have a proven track record in enhancing human capabilities for decision making in complex situations involving uncertainty and multiple conflicting objectives. In addition to theoretical and algorithmic issues, a crucial element of such systems is their user interface, which assists human decision makers in framing their decision problems, capturing their knowledge in terms of models and also gaining insight into the results of the systems’ reasoning.
Faculty/Lab: Decision Systems Laboratory, Dr. Marek J Druzdzel.