Liang Gou

CollabSeer: a search engine for collaboration discovery

Collaborative research has been increasingly popular and important in academic circles. However, there is no open platform available for scholars or scientists to effectively discover potential collaborators. This paper discusses CollabSeer, an open system to recommend potential research collaborators for scholars and scientists. CollabSeer discovers collaborators based on the structure of the coauthor network and a users research interests. Currently, three different network structure analysis methods that use vertex similarity are supported in CollabSeer: Jaccard similarity, cosine similarity, and our relation strength similarity measure. Users can also request a recommendation by selecting a topic of interest. The topic of interest list is determined by CollabSeers lexical analysis module, which analyzes the key phrases of previous publications. The CollabSeer system is highly modularized making it easy to add or replace the network analysis module or users topic of interest analysis module. CollabSeer integrates the results of the two modules to recommend collaborators to users. Initial experimental results over a subset of the CiteSeerX database show that CollabSeer can efficiently discover prospective collaborators.

Discovering missing links in networks using vertex similarity measures

Vertex similarity measure is a useful tool to discover the hidden relationships of vertices in a complex network. We introduce relation strength similarity (RSS), a vertex similarity measure that could better capture potential relationships of real world network structure. RSS is unique in that is is an asymmetric measure which could be used for a more general purpose social network analysis; allows users to explicitly specify the relation strength between neighboring vertices for initialization; and offers a discovery range parameter could be adjusted by users for extended network degree search. To show the potential of vertex similarity measures and the superiority of RSS over other measures, we conduct experiments on two real networks, a biological network and a coauthorship network. Experimental results show that RSS is better in discovering the hidden relationships of the networks.

Social network document ranking

In search engines, ranking algorithms measure the importance and relevance of documents mainly based on the contents and relationships between documents. User attributes are usually not considered in ranking. This user-neutral approach, however, may not meet the diverse interests of users, who may demand different documents even with the same queries. To satisfy this need for more personalized ranking, we propose a ranking framework. Social Network Document Rank (SNDocRank), that considers both document contents and the relationship between a searched and document owners in a social network. This method combined the traditional tf-idf ranking for document contents with out Multi-level Actor Similarity (MAS) algorithm to measure to what extent document owners and the searcher are structurally similar in a social network. We implemented our ranking method in simulated video social network based on data extracted from YouTube and tested its effectiveness on video search. The results show that compared with the traditional ranking method like tf-idfs the SNDocRank algorithm returns more relevant documents. More specifically, a searcher can get significantly better results be being in a larger social network, having more friends, and being associated with larger local communities in a social network.

SNDocRank: a social network-based video search ranking framework

Multimedia ranking algorithms are usually user-neutral and measure the importance and relevance of documents by only using the visual contents and meta-data. However, users interests and preferences are often diverse, and may demand different results even with the same queries. How can we integrate user interests in ranking algorithms to improve search results? Here, we introduce Social Network Document Rank (SNDocRank), a new ranking framework that considers a searchers social network, and apply it to video search. SNDocRank integrates traditional tf-idf ranking with our Multi-level Actor Similarity (MAS) algorithm, which measures the similarity between social networks of a searcher and document owners. Results from our evaluation study with a social network and video data from YouTube show that SNDocRank offers search results more relevant to users interests than other traditional ranking methods.

MobiSNA: a mobile video social network application

This paper presents MobiSNA -- a mobile video social networking application that supports the exploration, sharing, and creation of video contents through social networks. The MobiSNA project provides the user with an easy to use experience of accessing video content from mobile devices (e.g., mobile phones, PDAs) over wireless broadband networks (e.g., 4G networks). This demo focuses on the key functions of MobiSNA which support social network-based video exploration, real-time video sharing, video blogging, video interest groups, and video story construction. A system architecture of MobiSNA is also proposed.

Capturing missing edges in social networks using vertex similarity

We introduce the graph vertex similarity measure, Relation Strength Similarity (RSS), that utilizes a networks topology to discover and capture similar vertices. The RSS has the advantage that it is asymmetric; can be used in a weighted network; and has an adjustable discovery range parameter that enables exploration of friend of friend connections in a social network. To evaluate RSS we perform experiments on a coauthorship network from the CiteSeerX database. Our method significantly outperforms other vertex similarity measures in terms of the ability to predict future coauthoring behavior among authors in the CiteSeerX database for the near future 0 to 4 years out and reasonably so for 4 to 6 years out.

SNDocRank: document ranking based on social networks

To improve the search results for socially-connect users, we propose a ranking framework, Social Network Document Rank (SNDocRank). This framework considers both document contents and the similarity between a searcher and document owners in a social network and uses a Multi-level Actor Similarity (MAS) algorithm to efficiently calculate user similarity in a social network. Our experiment results based on YouTube data show that compared with the tf-idf algorithm, the SNDocRank method returns more relevant documents of interest. Our findings suggest that in this framework, a searcher can improve search by joining larger social networks, having more friends, and connecting larger local communities in a social network.

Predicting recent links in FOAF networks

For social networks, prediction of new links or edges can be important for many reasons, in particular for understanding future network growth. Recent work has shown that graph vertex similarity measures are good at predicting graph link formation for the near future, but are less effective in predicting further out. This could imply that recent links can be more important than older links in link prediction. To see if this is indeed the case, we apply a new relation strength similarity (RSS) measure on a coauthorship network constructed from a subset of the CiteSeerX dataset to study the power of recency. We choose RSS because it is one of the few similarity measures designed for weighted networks and easily models FOAF networks. By assigning different weights to the links according to authors coauthoring history, we show that recency is helpful in predicting the formation of new links.

SocialNetSense: Supporting sensemaking of social and structural features in networks with interactive visualization

Increasingly, social network datasets contain social attribute information about actors and their relationship. Analyzing such network with social attributes requires making sense of not only its structural features, but also the relationship between social features in attributes and network structures. Existing social network analysis tools are usually weak in supporting complex analytical tasks involving both structural and social features, and often overlook users needs for sensemaking tools that help to gather, synthesize, and organize information of these features. To address these challenges, we propose a sensemaking framework of social-network visual analytics in this paper. This framework considers both bottom-up processes, which are about constructing new understandings based on collected information, and top-down processes, which concern using prior knowledge to guide information collection, in analyzing social networks from both social and structural perspectives. The framework also emphasizes the externalization of sensemaking processes through interactive visualization. Guided by the framework, we develop a system, SocialNetSense, to support the sensemaking in visual analytics of social networks with social attributes. The example of using our system to analyze a scholar collaboration network shows that our approach can help users gain insight into social networks both structurally and socially, and enhance their process awareness in visual analytics.

Towards the Discovery of Diseases Related by Genes Using Vertex Similarity Measures

Discovering the relationships of gene to gene, gene to its related diseases, and diseases implicated in common genes is important. However, traditional biological methods can be expensive. Here, we show that the diseases implicated in common genes and the genes related to a multiple-gene disease can be inferred by the vertex similarity measures, a type of method to find the similar vertices in a network based on its structure. The relationship among diseases and the relationship among genes are modeled as two biological networks: human disease network and disease gene network. We apply the vertex similarity among the vertices in the human disease network to infer the diseases implicated in common genes. By similar manner, we utilize vertex similarity measures on the disease gene network to infer the genes related to a common multiple-gene disease. Experimental results demonstrate the potential of vertex similarity as an inexpensive approach to infer the possible links between genes and between diseases. We also develop a system to visualize and get a better understanding about the relationships among diseases and genes.