Browsing by Author "Chiang, Meng-Fen"

Now showing 1 - 14 of 14

A Temporal Probabilistic Model for Dynamic Circle Recommendation in Mobile Applications
(2013)
Chou, Fan-Kai
;
Chiang, Meng-Fen
;
Peng, Wen-Chih
;
資訊工程學系
;
Department of Computer Science
This paper presents a novel framework for dynamic circle recommendation for a query user at a given time point from historical communication logs. We identify the fundamental factors that govern interactions and aim to automatically form friend circles for scenarios, such as, who should I share the photo with in the early morning? Whose post should be listed on top of my Facebook Wall feed at night? We develop a temporal probabilistic model that not only captures temporal tendencies between the query user and each friend candidate but also blends frequency and recency into circle formation. Experimental results on Enron dataset and Call Detail Records prove the effectiveness of dynamic circle formation with proposed temporal probabilistic model.
Discovering popular co-cited communities in blogspaces
(2008)
Chiang, Meng-Fen
;
Peng, Wen-Chih
;
Lo, Chia-Hao
;
資訊工程學系
;
Department of Computer Science
In a blogspace, citation behaviors reflect interests of bloggers. To fully get insight into the latent information in a blogspace, in this paper, we intend to mine popular co-cited communities consisting of core sets and follower sets. In such a cocited community, bloggers in the core set are frequently cited by bloggers in the follower set and the co-citation behaviors among bloggers are very intensive. Through co-citations, not only the popular core-set nodes but also the followers can be discovered. As such, one could effectively obtain the trends of discussion among bloggers. Explicitly, two kinds of co-cited communities are exploited: perfect co-cited community and approximate co-cited community. Given a blogspace, we first transform this blogspace into a transaction database. Then, by exploring frequent closed itemsets, we are able to discover perfect co-cited communities. Then, a greedy algorithm is proposed to derive approximate co-cited communities. To evaluate our community structures mined, we conduct extensive experiments on del.icio.us dataset. The experimental results demonstrate the effectiveness of our proposed framework.
Distant-Time Location Prediction in Low-Sampling-Rate Trajectories
(2013)
Chiang, Meng-Fen
;
Zhu, Wen-Yuan
;
Peng, Wen-Chih
;
Yu, Philip S.
;
資訊工程學系
With the growth of location-based services and social services, low-sampling-rate trajectories from check-in data or photos with geo-tag information becomes ubiquitous. In general, most detailed moving information in low-sampling-rate trajectories are lost. Prior works have elaborated on distant-time location prediction in high-sampling-rate trajectories. However, existing prediction models are pattern-based and thus not applicable due to the sparsity of data points in low-sampling-rate trajectories. For example, it becomes difficult to derive trajectory patterns, let alone utilizing trajectory patterns for distant-time location prediction. In this paper, given a query time, the current location and time, we aim to predict the location of an object at the query time. To address the sparsity in low-sampling-rate trajectories, we develop a Reachability-based prediction model on Time-constrained Mobility Graph (abbreviated as RTMG) to predict locations for distant-time queries. Specifically, we design an adaptive temporal exploration approach to extract effective supporting trajectories that are temporally close to the query time. These data points are then represented as a Time-constrained user mobility Graph (refers to as TG). In light of TG, we further derive the reachability probabilities among locations in TG. Thus, a location with maximum reachability from the current location among all possible locations in supporting trajectories is considered as the prediction result. To efficiently process queries, we proposed an index structure SOIT to organize location records for on-line query processing. We conduct extensive experiments on real low-sampling-rate datasets and demonstrate the effectiveness and efficiency of RTMG.
Emotion-based music recommendation by affinity discovery from film music
(2009-05-01)
Shan, Man-Kwan
;
Kuo, Fang-Fei
;
Chiang, Meng-Fen
;
Lee, Suh-Yin
;
資訊工程學系
With the growth of digital music, the development of music recommendation is helpful for users to pick desirable music pieces from a huge repository of music. The existing music recommendation approaches are based on a user's preference on music. However, sometimes, it might better meet users' requirement to recommend music pieces according to emotions. In this paper, we propose a novel framework for emotion-based music recommendation. The core of the recommendation framework is the construction of the music emotion model by affinity discovery from film music, which plays an important role in conveying emotions in film. We investigate the music feature extraction and propose the Music Affinity Graph and Music Affinity Graph-Plus algorithms for the construction of music emotion model. Experimental result shows the proposed emotion-based music recommendation achieves 85% accuracy in average. (C) 2008 Elsevier Ltd. All rights reserved.
Exploring heterogeneous information networks and random walk with restart for academic search
(2013-07-01)
Chiang, Meng-Fen
;
Liou, Jiun-Jiue
;
Wang, Jen-Liang
;
Peng, Wen-Chih
;
Shan, Man-Kwan
In this paper, we explore heterogenous information networks in which each vertex represents one entity and the edges reflect linkage relationships. Heterogenous information networks contain vertices of several entity types, such as papers, authors and terms, and hence can fully reflect multiple linkage relationships among different entities. Such a heterogeneous information network is similar to a mixed media graph (MMG). By representing a bibliographic dataset as an MMG, the performance obtained when searching relevant entities (e.g., papers) can be improved. Furthermore, our academic search enables multiple-entity search, where a variety of entity search results are provided, such as relevant papers, authors and conferences, via a one-time query. Explicitly, given a bibliographic dataset, we propose a Global-MMG, in which a global heterogeneous information network is built. When a user submits a query keyword, we perform a random walk with restart (RWR) to retrieve papers or other types of entity objects. To reduce the query response time, algorithm Net-MMG (standing for NetClus-based MMG) is developed. Algorithm Net-MMG first divides a heterogeneous information network into a collection of sub-networks. Afterward, the Net-MMG performs a RWR on a set of selected relevant sub-networks. We implemented our academic search and conducted extensive experiments using the ACM Digital Library. The experimental results show that by exploring heterogeneous information networks and RWR, both the Global-MMG and Net-MMG achieve better search quality compared with existing academic search services. In addition, the Net-MMG has a shorter query response time while still guaranteeing good quality in search results.
Exploring latent browsing graph for question answering recommendation
(2012-09-01)
Chiang, Meng-Fen
;
Peng, Wen-Chih
;
Yu, Philip S.
;
交大名義發表
;
National Chiao Tung University
"In this paper, we develop a framework of Question Answering Pages (referred to as QA pages) recommendation. Our proposed framework consists of the two modules: the off-line module to determine the importance of QA pages and the on-line module for on-line QA page recommendation. In the off-line module, we claim that the importance of QA pages could be discovered from user click streams. If the QA pages are of higher importance, many users will click and spend their time on these QA pages. Moreover, the relevant relationships among QA pages are captured by the browsing behavior on these QA pages. As such, we exploit user click streams to model the browsing behavior among QA pages as QA browsing graph structures. The importance of QA pages is derived from our proposed QA browsing graph structures. However, we observe that the QA browsing graph is sparse and that most of the QA pages do not link to other QA pages. This is referred to as a sparsity problem. To overcome this problem, we utilize the latent browsing relations among QA pages to build a QA Latent Browsing Graph. In light of QA latent browsing graph, the importance score of QA pages (referred to as Latent Browsing Rank) and the relevance score of QA pages (referred to as Latent Browsing Recommendation Rank) are proposed. These scores demonstrate the use of a QA latent browsing graph not only to determine the importance of QA pages but also to recommend QA pages. We conducted extensive empirical experiments on Yahoo! Asia Knowledge Plus to evaluate our proposed framework."
Inferring Distant-Time Location in Low-Sampling-Rate Trajectories
(2013-01-01)
Chiang, Meng-Fen
;
Lin, Yung-Hsiang
;
Peng, Wen-Chih
;
Yu, Philip S.
;
資訊工程學系
With the growth of location-based services and social services, low sampling-rate trajectories from check-in data or photos with geotag information becomes ubiquitous. In general, most detailed moving information in low-sampling-rate trajectories are lost. Prior works have elaborated on distant-time location prediction in highsampling-rate trajectories. However, existing prediction models are pattern-based and thus not applicable due to the sparsity of data points in low-sampling-rate trajectories. To address the sparsity in low-sampling-rate trajectories, we develop a Reachability-based prediction model on Time-constrained Mobility Graph (RTMG) to predict locations for distant-time queries. Specifically, we design an adaptive temporal exploration approach to extract effective supporting trajectories that are temporally close to the query time. Based on'the supporting trajectories, a Time-constrained mobility Graph (TG) is constructed to capture mobility information at the given query time. In light of TG, we further derive the reachability probabilities among locations in TG. Thus, a location with maximum reachability from the current location among all possi ble locations in supporting trajectories is considered as the prediction result. To efficiently process queries, we proposed the index structure Sorted Interval-Tree (SOIT) to organize location records. Extensive experiments with real data demonstrated the effectiveness and efficiency of RTMG. First, RTMG with adapthie temporal exploration significantly outperforms the existing pattern-based prediction model HPM [2] over varying data sparsity in terms of higher accuracy and higher coverage. Also, the proposed index structure SOIT can efficiently speedup RTMG in large-scale trajectory dataset. In the future, we could extend RTMG by considering more factors (e.g., staying durations in locations, application usages in smart phones) to further improve the prediction accuracy.
Inferring Potential Users in Mobile Social Networks
(2014)
Hsu, Tsung-Hao
;
Chen, Chien-Cheng
;
Chiang, Meng-Fen
;
Hsu, Kuo-Wei
;
Peng, Wen-Chih
In mobile social networks, users can communicate with each other over different telecom operators. Thus, for telecom operators, how to attract new customers is a significant issue. The work of churn prediction is to determine whether a customer would leave soon. Differing from churn prediction, our work is to find those users who are likely to join target services from the competitors in the near future, where these users are called potential users. To infer potential users, we propose a framework including feature extraction, feature selection, and classifier learning to solve the problem. First, we construct a heterogeneous information network from the call detail records of users. Then, we extract the explicit features from potential users\' interaction behavior in the heterogeneous information network. Moreover, because users are influenced by their community, we extract community-based implicit features of potential users. After feature extraction, we explore the Information Gain to select the effective features. We use the effective explicit and implicit features to learn potential user classifiers, and use the classifiers to determine the potential users. Finally, we conduct experiments on real datasets. The results of our experiments show that the features extracted by our proposed method can improve the accuracy of inferring potential users.
Inferring Social Relationships across Social Networks for Viral Marketing
(2012-01-01)
Hsu, Tsung-Hao
;
Chiang, Meng-Fen
;
Peng, Wen-Chih
;
交大名義發表
;
National Chiao Tung University
Node classification in social networks is a useful and important technique that has been widely studied in recent years. Many existing node classification methods mainly focus on exploiting structural and attribute information to identify node classes. However, the information in an emerging information network is usually limited. For example, a social networking platform that includes a few registered users(referred to as active users) and a significant amount of new comers (referred to as non-active users) with very sparse interactions among registered users. Under this circumstances, distinguishing the users that is likely to be active in the future from large-scale new comers becomes challenging. In this paper, we propose a hybrid classification model, which can distinguish whether a nonactive user will become an active user in the future by incorporating multiple relations through a unified ranking measure. Particularly, given a friendship network and a mobile communication network, we aim to discover a small set of users, who are likely to become active users in the future, from a massive amount of non-active users. X We conducted extensive experiments to demonstrate the effectiveness of our hybrid ranking model as well as report several empirical observations from real data sets.
Inferring Social Relationships across Social Networks for Viral Marketing
(2012-01-01)
Hsu, Tsung-Hao
;
Chiang, Meng-Fen
;
Peng, Wen-Chih
;
資訊工程學系
;
Department of Computer Science
Node classification in social networks is an important problem that has been widely studied in recent years. Several existing node classification methods mainly focus on identifying node classes by exploiting structural and attribute information. However, the information in an emerging information network is usually limited. For example, an emerging social networking service usually has very few registered users (referred to as active users) and a significant amount of new comers (referred to as non-active users) resulting in very sparse interactions among active users. Under this circumstances, distinguishing the users that is likely to be an active user in the future from large-scale new comers becomes challenging. In this paper, we propose a hybrid classification model, which can distinguish whether a non-active user will become an active user in the future by incorporating multiple relations through a unified ranking measure. More specifically, given a friendship network and a mobile communication network, we aim to discover a ranked list of users, who are likely to become active users in the future, from a massive amount of non-active users. We reported several empirical observations from real data sets and conducted extensive experiments to demonstrate the effectiveness of our hybrid classification model and ranking strategy.
Mining and clustering mobility evolution patterns from social media for urban informatics
(2016-05)
Chen, Chien-Cheng
;
Chiang, Meng-Fen
;
Peng, Wen-Chih
;
交大名義發表
;
National Chiao Tung University
In this paper, given a set of check-in data, we aim at discovering representative daily movement behavior of users in a city. For example, daily movement behavior on a weekday may show users moving from one to another spatial region associated with time information. Since check-in data contain both spatial and temporal information, we propose a mobility evolution pattern to capture the daily movement behavior of users in a city. Furthermore, given a set of daily mobility evolution patterns, we formulate their similarity distances and then discover representative mobility evolution patterns via the clustering process. Representative mobility evolution patterns are able to infer major movement behavior in a city, which could bring some valuable knowledge for urban planning. Specifically, mobility evolution patterns consist of segments with the spatial region distribution and the corresponding time interval. To measure good segmentation from a set of check-in data, we formulate the problem of mining evolution patterns as a compression problem. In particular, we compute the representation length of the patterns based on the Minimum Description Length principle. Since the number of daily mobility evolution patterns is huge, we further cluster the daily mobility evolution patterns into groups and discover representative patterns. Note that we use the concept of locality-sensitive hashing to accelerate the cluster performance. To evaluate our proposed algorithms, we conducted experiments on the Gowalla and Brightkite datasets, and the experimental results show the effectiveness and efficiency of our proposed algorithms.
Mining Mobility Evolution from Check-in Datasets
(2014-01-01)
Chiang, Meng-Fen
;
Chen, Chien-Cheng
;
Peng, Wen-Chih
;
Yu, Philip S.
;
交大名義發表
The advances in location-acquisition and smart phone technologies have led to a myriad of location-based social media. Therefore, analyzing the increasing amount of spatio-temporal data emerges as an important topic. Most studies on geographic data mining focus on exploring static mobility patterns. As the amount of incoming data streams increases, revealing the temporal aspect of user mobility patterns is worth investigating. This paper targets on mining user mobility patterns over time (referred to as mobility evolution) from streams of check-in records. Intuitively, at each time slot, a mobility pattern indicates spatial regions where users stay. Therefore, given a set of time slots, mobility evolution refers a sequence of spatial regions at each time slot. Note that nearby time slots may have similar spatial region distribution. Thus, given check-in datasets, we use the idea of data compression to obtain a sequence of representative segments, where each representative segment captures spatial region distribution at the corresponding time interval. To measure the quality of a segmentation result, we propose a representation cost function based on the Minimum Description Length (MDL) principle. In addition, because deriving the sequence of segments incurs expensive computational cost, we propose a family of greedy algorithms for segmentation to serve diverse requirements: efficient compression, informative compression, and cost-effective compression. Besides, to handle the massive amount of incoming check-in data, we also propose an incremental compression approach to incrementally update the mobility evolution. We conduct experiments on Foursquare datasets to demonstrate both the effectiveness and efficiency of our proposed algorithms.
Relevance feedback for category search in music retrieval based on semantic concept learning
(2008-09-01)
Shan, Man-Kwan
;
Chiang, Meng-Fen
;
Kuo, Fang-Fei
;
資訊工程學系
;
Department of Computer Science
Traditional content-based music retrieval systems retrieve a specific music object which is similar to what a user has requested. However, the need exists for the development of category search for the retrieval of a specific category of music objects which share a common semantic concept. The concept of category search in content-based music retrieval is subjective and dynamic. Therefore, this paper investigates a relevance feedback mechanism for category search of polyphonic symbolic music based on semantic concept learning. For the consideration of both global and local properties of music objects, a segment-based music object modeling approach is presented. Furthermore, in order to discover the user semantic concept in terms of discriminative features of discriminative segments, a concept learning mechanism based on data mining techniques is proposed to find the discriminative characteristics between relevant and irrelevant objects. Moreover, three strategies, the Most-Positive, the Most-Informative, and the Hybrid, to return music objects concerning user relevance judgments are investigated. Finally, comparative experiments are conducted to evaluate the effectiveness of the proposed relevance feedback mechanism. Experimental results show that, for a database of 215 polyphonic music objects, 60% average precision can be achieved through the use of the proposed relevance feedback mechanism.
Trajectory Pattern Mining: Exploring Semantic and Time Information
(2016-01-01)
Chen, Chien-Cheng
;
Chiang, Meng-Fen
;
交大名義發表
;
National Chiao Tung University
With the development of GPS and the popularity of smart phones and wearable devices, users can easily log their daily trajectories. Prior works have elaborated on mining trajectory patterns from raw trajectories. Trajectory patterns consist of hot regions and the sequential relationships among them, where hot regions refer the spatial regions with a higher density of data points. Note that some hot regions do not have any meaning for users. Moreover, trajectory patterns do not have explicit time information or semantic information. To enrich trajectory patterns, we propose semantic trajectory patterns which are referred to as the moving patterns with spatial, temporal, and semantic attributes. Given a user trajectory, we aim at mining frequent semantic trajectory patterns. Explicitly, we extract the three attributes from a raw trajectory, and convert it into a semantic mobility sequence. Given such a semantic mobility sequence, we propose two algorithms to discover frequent semantic trajectory patterns. The first algorithm, MB (standing for matching-based algorithm), is a naive method to find frequent semantic trajectory patterns. It generates all possible patterns and extracts the occurrence of the patterns from the semantic mobility sequence. The second algorithm, PS (standing for PrefixSpan-based algorithm), is developed to efficiently mine semantic trajectory patterns. Due to the good efficiency of PrefixSpan, algorithm PS will fully utilize the advantage of PrefixSpan. Since the semantic mobility sequence contains three attributes, we need to further transform it into a raw sequence before using algorithm PrefixSpan. Therefore, we propose the SS algorithm (standing for sequence symbolization algorithm) to achieve this purpose. To evaluate our proposed algorithms, we conducted experiments on the real datasets of Google Location History, and the experimental results show the effectiveness and efficiency of our proposed algorithms.