The Experts below are selected from a list of 48 Experts worldwide ranked by ideXlab platform
Qiao Deng - One of the best experts on this subject based on the ideXlab platform.
-
Friendship Link recommendation based on content structure information
Web-Age Information Management, 2015Co-Authors: Xiaoming Zhang, Qiao DengAbstract:Intuitively, a Friendship Link between two users can be recommended based on the similarity of their generated text content or structure information. Although this problem has been extensively studied, the challenge of how to effectively incorporate the information from the social interaction and user generated content remains largely open. We propose a model (LRCS) to recommend user’s potential friends by incorporating user’s generated content and structure features. First, network users are clustered based on the similarity of user’s interest and structural features. Users in the same cluster with the query user are considered as the candidate friends. Then, a weighted SimRank algorithm is proposed to recommend the most similar users as the friends. Experiments on two real-life datasets show the superiority of our approach.
-
WAIM - Friendship Link Recommendation Based on Content Structure Information
Web-Age Information Management, 2015Co-Authors: Xiaoming Zhang, Qiao DengAbstract:Intuitively, a Friendship Link between two users can be recommended based on the similarity of their generated text content or structure information. Although this problem has been extensively studied, the challenge of how to effectively incorporate the information from the social interaction and user generated content remains largely open. We propose a model (LRCS) to recommend user’s potential friends by incorporating user’s generated content and structure features. First, network users are clustered based on the similarity of user’s interest and structural features. Users in the same cluster with the query user are considered as the candidate friends. Then, a weighted SimRank algorithm is proposed to recommend the most similar users as the friends. Experiments on two real-life datasets show the superiority of our approach.
Xiaoming Zhang - One of the best experts on this subject based on the ideXlab platform.
-
Friendship Link recommendation based on content structure information
Web-Age Information Management, 2015Co-Authors: Xiaoming Zhang, Qiao DengAbstract:Intuitively, a Friendship Link between two users can be recommended based on the similarity of their generated text content or structure information. Although this problem has been extensively studied, the challenge of how to effectively incorporate the information from the social interaction and user generated content remains largely open. We propose a model (LRCS) to recommend user’s potential friends by incorporating user’s generated content and structure features. First, network users are clustered based on the similarity of user’s interest and structural features. Users in the same cluster with the query user are considered as the candidate friends. Then, a weighted SimRank algorithm is proposed to recommend the most similar users as the friends. Experiments on two real-life datasets show the superiority of our approach.
-
WAIM - Friendship Link Recommendation Based on Content Structure Information
Web-Age Information Management, 2015Co-Authors: Xiaoming Zhang, Qiao DengAbstract:Intuitively, a Friendship Link between two users can be recommended based on the similarity of their generated text content or structure information. Although this problem has been extensively studied, the challenge of how to effectively incorporate the information from the social interaction and user generated content remains largely open. We propose a model (LRCS) to recommend user’s potential friends by incorporating user’s generated content and structure features. First, network users are clustered based on the similarity of user’s interest and structural features. Users in the same cluster with the query user are considered as the candidate friends. Then, a weighted SimRank algorithm is proposed to recommend the most similar users as the friends. Experiments on two real-life datasets show the superiority of our approach.
Yuxiu Zhang - One of the best experts on this subject based on the ideXlab platform.
-
The Determinants and Consequences of Friendship Composition
2013Co-Authors: Jason M. Fletcher, Stephen L. Ross, Yuxiu ZhangAbstract:This paper examines the demographic pattern of Friendship Links among youth and the impact of those patterns on own educational outcomes using the Friendship network data in the Add Health. We develop and estimate a reduced form matching model to predict Friendship Link formation and identify the parameters based on across-cohort, within school variation in the "supply" of potential friends. We find novel evidence showing that small increases in the share of students with college educated mothers raises the likelihood of Friendship Links among students with high maternal education, and that small increases in the share of minority students increases the level of racial homophily in Friendship patterns. We then use the predicted Friendship Links from the matching model in an instrumental variable analysis, and find positive effects of friends' high socioeconomic status, as measured by parental education, on own GPA outcomes among girls. The GPA effects are likely driven by science and English grades, and through non-cognitive factors.
-
The Determinants and Consequences of Friendship Composition
2013Co-Authors: Jason M. Fletcher, Stephen L. Ross, Yuxiu ZhangAbstract:This paper examines the demographic pattern of Friendship Links among youth and the impact of those patterns on own educational outcomes using the Friendship network data in the Add Health. We develop and estimate a reduced form matching model to predict Friendship Link formation and identify the parameters based on across-cohort, within school variation in the "supply" of potential friends. Our model provides novel evidence on the impact of small changes in peer demographic composition on the pattern of Friendship Links. The evidence suggests, for example, that increases in the share of African-American or Hispanic students leads to reductions in the incidence of cross race Friendships. We then use the predicted Friendship Links from the model in an instrumental variable analysis of the effects of friends' socioeconomic status, as measured by parental education, on own grade point average outcomes. Although the conditional correlation between Friendship composition and grade point average suggests large associations between friends' characteristics and own grades, this effect is robust only for females in the instrumental variable analysis. We then present evidence that the GPA effects are driven by science and English grades and a mechanism is likely through non-cognitive factors.
Alireza Bagheri - One of the best experts on this subject based on the ideXlab platform.
-
Presenting new collaborative Link prediction methods for activity recommendation in Facebook
Neurocomputing, 2016Co-Authors: Amin Shahmohammadi, Ehsan Khadangi, Alireza BagheriAbstract:One of the common methods used in recommender systems is collaborative filtering methods. In these methods, same-interest users' preferences are often recommended to each other based on examining their past interests. On the other hand, one of the recommendation methods in social networks is to measure the proximity of the two nodes in the graph. Although many researchers have dealt with Friendship Link prediction in different online social networks, very little notice has been spent on activity prediction based on different users' interactions. The main objective of this paper is the use of collaborative filtering methods for activity prediction and recommendation both for pairs of users without any interaction background and also for user pairs with the activity background. In this regard, a new concept is initially presented named as "collaborative path". Then based on the collaborative path, four directed proximity measures are proposed. In addition, three new algorithms, including two algorithms based on collaborative random walks, one for mixed network and one for multilayer network and the Collaborative-Association-Rule algorithm are presented. Finally, in order to evaluate our proposed methods, we perform some experiments on the dataset of different Facebook activity networks including like, comment, post, and share networks. The results show that the proposed collaborative methods deal with the activity prediction well without suffering from the cold start problem, and outperform the existing state of the art methods.
Jason M. Fletcher - One of the best experts on this subject based on the ideXlab platform.
-
The Determinants and Consequences of Friendship Composition
2013Co-Authors: Jason M. Fletcher, Stephen L. Ross, Yuxiu ZhangAbstract:This paper examines the demographic pattern of Friendship Links among youth and the impact of those patterns on own educational outcomes using the Friendship network data in the Add Health. We develop and estimate a reduced form matching model to predict Friendship Link formation and identify the parameters based on across-cohort, within school variation in the "supply" of potential friends. We find novel evidence showing that small increases in the share of students with college educated mothers raises the likelihood of Friendship Links among students with high maternal education, and that small increases in the share of minority students increases the level of racial homophily in Friendship patterns. We then use the predicted Friendship Links from the matching model in an instrumental variable analysis, and find positive effects of friends' high socioeconomic status, as measured by parental education, on own GPA outcomes among girls. The GPA effects are likely driven by science and English grades, and through non-cognitive factors.
-
The Determinants and Consequences of Friendship Composition
2013Co-Authors: Jason M. Fletcher, Stephen L. Ross, Yuxiu ZhangAbstract:This paper examines the demographic pattern of Friendship Links among youth and the impact of those patterns on own educational outcomes using the Friendship network data in the Add Health. We develop and estimate a reduced form matching model to predict Friendship Link formation and identify the parameters based on across-cohort, within school variation in the "supply" of potential friends. Our model provides novel evidence on the impact of small changes in peer demographic composition on the pattern of Friendship Links. The evidence suggests, for example, that increases in the share of African-American or Hispanic students leads to reductions in the incidence of cross race Friendships. We then use the predicted Friendship Links from the model in an instrumental variable analysis of the effects of friends' socioeconomic status, as measured by parental education, on own grade point average outcomes. Although the conditional correlation between Friendship composition and grade point average suggests large associations between friends' characteristics and own grades, this effect is robust only for females in the instrumental variable analysis. We then present evidence that the GPA effects are driven by science and English grades and a mechanism is likely through non-cognitive factors.
