Chien Chin Chen

PVA: A Self-Adaptive Personal View Agent

In this paper, we present PVA, an adaptive personal view information agent system for tracking, learning and managing user interests in Internet documents. PVA consists of three parts: a proxy, personal view constructor, and personal view maintainer. The proxy logs the users activities and extracts the users interests without user intervention. The personal view constructor mines user interests and maps them to a class hierarchy (i.e., personal view). The personal view maintainer synchronizes user interests and the personal view periodically. When user interests change, in PVA, not only the contents, but also the structure of the user profile are modified to adapt to the changes. In addition, PVA considers the aging problem of user interests. The experimental results show that modulating the structure of the user profile increases the accuracy of a personalization system.

Life cycle modeling of news events using aging theory

In this paper, an adaptive news event detection method is proposed. We consider a news event as a life form and propose an aging theory to model its life span. A news event becomes popular with a burst of news reports, and it fades away with time. We incorporate the proposed aging theory into the traditional single-pass clustering algorithm to model life spans of news events. Experiment results show that the proposed method has fairly good performance for both long-running and short-term events compared to other approaches.

An effective recommendation method for cold start new users using trust and distrust networks

Recommendation systems analyze the purchasing behavior (e.g., item ratings) of users to learn about their preferences and recommend products or services that may be of interest to them. However, as new users require time to become familiar with recommendation systems, the systems usually have limited information about newcomers and have difficulty providing appropriate recommendations. This so-called new user cold start phenomenon has a serious impact on the performance of recommendation systems. As a result, there has been increasing research in recent years into new user cold start recommendation methods that try to provide useful item recommendations for cold start new users. The rationale behind much of the research is that recommending items to new users generally creates a sense of belonging and loyalty, and encourages them to frequently utilize recommendation systems. In this paper, we propose a cold start recommendation method for the new user that integrates a user model with trust and distrust networks to identify trustworthy users. The suggestions of these users are then aggregated to provide useful recommendations for cold start new users. Experiments based on the well-known Epinions dataset demonstrate the efficacy of the proposed method. Moreover, the method outperforms well-known recommendation methods for cold start new users in terms of the recall rate, F1 score, coverage rate, users coverage, and execution time, without a significant reduction in the precision of the recommendations.

An Aging Theory for Event Life-Cycle Modeling

An event can be described by a sequence of chronological documents from several information sources that together describe a story or happening. The goal of event detection and tracking is to automatically identify events and their associated documents during their life cycles. Conventional document clustering and classification techniques cannot effectively detect and track sequential events, as they ignore the temporal relationships among documents related to an event. The life cycle of an event is analogous to living beings. With abundant nourishment (i.e., related documents for the event), the life cycle is prolonged; conversely, an event or living fades away when nourishment is exhausted. Improper tracking algorithms often unnecessarily prolong or shorten the life cycle of detected events. In this paper, we propose an aging theory to model the life cycle of sequential events, which incorporates a traditional single-pass clustering algorithm to detect and track events. Our experiment results show that the proposed method achieves a better overall performance for both long-running and short-term events than previous approaches. Moreover, we find that the aging parameters of the aging schemes are profile dependent and that using proper profile-specific aging parameters improves the detection and tracking performance further

PVA: a self-adaptive personal view agent system

In this paper, we present PVA, an adaptive personal view information agent system to track, learn and manage, users interests in Internet documents. When users interests change, PVA, in not only the contents, but also in the structure of user profile, is modified to adapt to the changes. Experimental results show that modulating the structure of user profile does increase the accuracy of personalization systems.

TSCAN: a novel method for topic summarization and content anatomy

A topic is defined as a seminal event or activity along with all directly related events and activities. It is represented as a chronological sequence of documents by different authors published on the Internet. In this paper, we define a task called topic anatomy, which summarizes and associates core parts of a topic graphically so that readers can understand the content easily. The proposed topic anatomy model, called TSCAN, derives the major themes of a topic from the eigenvectors of a temporal block association matrix. Then, the significant events of the themes and their summaries are extracted by examining the constitution of the eigenvectors. Finally, the extracted events are associated through their temporal closeness and context similarity to form the evolution graph of the topic. Experiments based on the official TDT4 corpus demonstrate that the generated evolution graphs comprehensibly describe the storylines of topics. Moreover, in terms of content coverage and consistency, the produced summaries are superior to those of other summarization methods based on human composed reference summaries.

TSCAN: A Content Anatomy Approach to Temporal Topic Summarization

A topic is defined as a seminal event or activity along with all directly related events and activities. It is represented by a chronological sequence of documents published by different authors on the Internet. In this study, we define a task called topic anatomy, which summarizes and associates the core parts of a topic temporally so that readers can understand the content easily. The proposed topic anatomy model, called TSCAN, derives the major themes of a topic from the eigenvectors of a temporal block association matrix. Then, the significant events of the themes and their summaries are extracted by examining the constitution of the eigenvectors. Finally, the extracted events are associated through their temporal closeness and context similarity to form an evolution graph of the topic. Experiments based on the official TDT4 corpus demonstrate that the generated temporal summaries present the storylines of topics in a comprehensible form. Moreover, in terms of content coverage, coherence, and consistency, the summaries are superior to those derived by existing summarization methods based on human-composed reference summaries.

An adaptive threshold framework for event detection using HMM-based life profiles

When an event occurs, it attracts attention of information sources to publish related documents along its lifespan. The task of event detection is to automatically identify events and their related documents from a document stream, which is a set of chronologically ordered documents collected from various information sources. Generally, each event has a distinct activeness development so that its status changes continuously during its lifespan. When an event is active, there are a lot of related documents from various information sources. In contrast when it is inactive, there are very few documents, but they are focused. Previous works on event detection did not consider the characteristics of the events activeness, and used rigid thresholds for event detection. We propose a concept called life profile, modeled by a hidden Markov model, to model the activeness trends of events. In addition, a general event detection framework, LIPED, which utilizes the learned life profiles and the burst-and-diverse characteristic to adjust the event detection thresholds adaptively, can be incorporated into existing event detection methods. Based on the official TDT corpus and contest rules, the evaluation results show that existing detection methods that incorporate LIPED achieve better performance in the cost and F1 metrics, than without.

LIPED: HMM-based life profiles for adaptive event detection

In this paper, the proposed LIPED (LIfe Profile based Event Detection) employs the concept of life profiles to predict the activeness of event for effective event detection. A group of events with similar activeness patterns shares a life profile, modeled by a hidden Markov model. Considering the burst-and-diverse property of events, LIPED identifies the activeness status of event. As a result, LIPED balances the clustering precision and recall to achieve better F1 scores than other well known approaches evaluated on the official TDT1 corpus.

BioCreative V BioC track overview: collaborative biocurator assistant task for BioGRID

BioC is a simple XML format for text, annotations and relations, and was developed to achieve interoperability for biomedical text processing. Following the success of BioC in BioCreative IV, the BioCreative V BioC track addressed a collaborative task to build an assistant system for BioGRID curation. In this paper, we describe the framework of the collaborative BioC task and discuss our findings based on the user survey. This track consisted of eight subtasks including gene/protein/organism named entity recognition, protein–protein/genetic interaction passage identification and annotation visualization. Using BioC as their data-sharing and communication medium, nine teams, world-wide, participated and contributed either new methods or improvements of existing tools to address different subtasks of the BioC track. Results from different teams were shared in BioC and made available to other teams as they addressed different subtasks of the track. In the end, all submitted runs were merged using a machine learning classifier to produce an optimized output. The biocurator assistant system was evaluated by four BioGRID curators in terms of practical usability. The curators’ feedback was overall positive and highlighted the user-friendly design and the convenient gene/protein curation tool based on text mining. Database URL: http://www.biocreative.org/tasks/biocreative-v/track-1-bioc/