Yuchul Jung

Identifying controversial issues and their sub-topics in news articles

We tackle the problem of automatically detecting controversial issues and their subtopics from news articles. We define a controversial issue as a concept that invokes conflicting sentiments or views and a subtopic as a reason or factor that gives a particular sentiment or view to the issue. Conforming to the definitions, we propose a controversial issue detection method that considers the magnitude of sentiment information and the difference between the amounts of two different polarities. For subtopic identification, candidate phrases are generated and checked for containing five different features, some of which attempts to capture the relationship between the identified issue phrase and the candidate subtopic phrase. Through an experiment and analysis using the MPQA corpus consisting of news articles, we found that the proposed method is promising for both of the tasks although many additional research issues remain to be tapped in the future.

A hybrid mood classification approach for blog text

As an effort to detect the mood of a blog, regardless of the length and writing style, we propose a hybrid approach to detecting blog texts mood, which incorporates commonsense knowledge obtained from the general public (ConceptNet) and the Affective Norms English Words (ANEW) list. Our approach picks up blog texts unique features and compute simple statistics such as term frequency, n-gram, and point-wise mutual information (PMI) for the SVM classification method. In addition, to catch mood transitions in a given blog text, we developed a paragraph-level segmentation based on a mood flow analysis using a revised version of the GuessMood operation of ConceptNet and an ANEW-based affective sensing module. For evaluation, a mood corpus comprised of real blog texts has been built semi-automatically. Our experiments using the corpus show meaningful results for 4 mood types: happy, sad, angry, and fear.

Employing collective intelligence for user driven service creation

With advances in computing technologies and active user participation through smart devices such as the iPhone and Android, user needs are becoming varied and complex. It is quite natural, then, that a single Web service may not be sufficient to fully satisfy the diverse goals of users in their daily lives. A set of cohesively connected Web services/mashups may be able to deal with these goals. An increasing number of open APIs can facilitate various types of service compositions with users as the service creators. Recently, Internet, telecommunications, and third-party providers have opened their services to the public in the form of open APIs, a trend following the Web 2.0 paradigm. However, most service creation environments do not have sufficient knowledge (particularly, available services and their functionality) to support service creation by users. The problem of knowledge scarcity is that users may have difficulty in finding relevant open APIs for a given situation, finally resulting in rather straightforward types of service. In this article we present two kinds of collective intelligence for user-driven service creation: the users own experiences in service composition, and activity knowledge from the web. These collective intelligence types will aid in creating enduser service compositions by enforcing knowledge support in terms of user experiences and activity-aware functional semantics, and will finally accelerate the development of various kinds of converged applications. Using the beneficial roles of collective intelligence as key enablers of future service creation environments, this article also shows a new potential for user-driven composite services within the next few years.

Identifying Opinion Holders in Opinion Text from Online Newspapers

We propose an anaphor resolution based opinion holder identification method exploiting lexical and syntactic information. We tested our approach on online news documents and obtained 72.22% and 69.89% in accuracy for the task of non-anaphoric opinion holder resolution and the task of anaphoric opinion holder identification, respectively.

Use of place information for improved event tracking

The main purpose of topic detection and tracking (TDT) is to detect, group, and organize newspaper articles reporting on the same event. Since an event is a reported occurrence at a specific time and place and the unavoidable consequences, TDT can benefit from an explicit use of time and place information. In this work, we focused on place information, using time information as in the previous research. News articles were analyzed for their characteristics of place information, and a new topic tracking method was proposed to incorporate the analysis results on place information. Experiments show that appropriate use of place information extracted automatically from news articles indeed helps event tracking that identify news articles reporting on the same events.

Determining Mood for a Blog by Combining Multiple Sources of Evidence

Mood classification for blogs is useful in helping user-to-agent interaction for a variety of applications involving the web, such as user modeling, recommendation systems, and user interface fields. It is challenging at the same time because of the diversity of the characteristics of bloggers, their experiences, and the way moods are expressed. As an attempt to handle the diversity, we combine multiple sources of evidence for a mood type. Support vector machine based mood classifier (SVMMC) is integrated with mood flow analyzer (MFA) that incorporates commonsense knowledge obtained from the general public (i.e. ConceptNet), the affective norms english words (ANEW) list, and mood transitions. In combining the two different approaches, we employ a statistically weighted voting scheme based on the support vector machine (SVM). For evaluation, we have built a mood corpus consisting of manually annotated blogs, which amounts to over 4000 blogs. Our proposed method outperforms SVMMC by 5.68% in precision. The improvement is attributed to the strategy of choosing more trustable classification results in an interleaving fashion between the SVMMC and our MFA.Data-rich webpages are providing an increasingly important data source for web applications. While the problem of data object recognition is intensively discussed, it is mostly addressed as a separated process from the frontier task of relevant webpage identification. In this paper, we propose a method to leverage the classification result of data-rich webpages for efficient and scalable data object recognition. A novel context information is proposed, which can be inferred from the webpage classification and exploited in the bottom-up data object recognition. Experimental results show that the context information brings a 19% improvement in the running efficiency of the bottom- up data object recognition.

Integrating Robot Task Scripts with a Cognitive Architecture for Cognitive Human-Robot Interactions

In spite of the long history of intelligent humanoid robots, endowing human-like commonsense knowledge to a robot is still a difficult problem. Since a knowledge base consisting of a large number of rules and facts is not an efficient structure that can express situational and background knowledge for humanoid robots, more compact yet forgiving representation is required. Our proposal is to employ a script design that contains richness and diversity needed for robots task planning, in conjunction with a robust cognitive architecture called EM-ONE, the latest extant account of an implemented cognitive architecture. The script structure has its advantages in flexibility and extensibility for a variety of situations or tasks at hand, along with reusability. As the number of scripts increases, the coverage for diverseness of human-robot interaction (HRI) situation grows. In this paper, we discuss three cognitive models used as our cognitive architecture basis and describe our efforts for generating task scripts in a semi-automatic way by reusing the already existing scripts.

Cluster-based query expansion using external collections in medical information retrieval

Utilizing external collections to improve retrieval performance is challenging research because various test collections are created for different purposes. Improving medical information retrieval has also gained much attention as various types of medical documents have become available to researchers ever since they started storing them in machine processable formats. In this paper, we propose an effective method of utilizing external collections based on the pseudo relevance feedback approach. Our method incorporates the structure of external collections in estimating individual components in the final feedback model. Extensive experiments on three medical collections (TREC CDS, CLEF eHealth, and OHSUMED) were performed, and the results were compared with a representative expansion approach utilizing the external collections to show the superiority of our method.

A Multiple-Stage Approach to Re-ranking Medical Documents

The widespread use of the Web has radically changed the way people acquire medical information. Every day, patients, their caregivers, and doctors themselves search for medical information to resolve their medical information needs. However, search results provided by existing medical search engines often contain irrelevant or uninformative documents that are not appropriate for the purposes of the users. As a solution, this paper presents a method of re-ranking medical documents. The key concept of our method is to compute accurate similarity scores through multiple stages of re-ranking documents from the initial documents retrieved by a search engine. Specifically, our method combines query expansion with abbreviations, query expansion with discharge summary, clustering-based document scoring, centrality-based document scoring, and pseudo relevance feedback with relevance model. The experimental results from participating in Task 3a of the CLEF 2014 eHealth show the performance of our method.

Identifying Key Hospital Service Quality Factors in Online Health Communities

Background The volume of health-related user-created content, especially hospital-related questions and answers in online health communities, has rapidly increased. Patients and caregivers participate in online community activities to share their experiences, exchange information, and ask about recommended or discredited hospitals. However, there is little research on how to identify hospital service quality automatically from the online communities. In the past, in-depth analysis of hospitals has used random sampling surveys. However, such surveys are becoming impractical owing to the rapidly increasing volume of online data and the diverse analysis requirements of related stakeholders. Objective As a solution for utilizing large-scale health-related information, we propose a novel approach to identify hospital service quality factors and overtime trends automatically from online health communities, especially hospital-related questions and answers. Methods We defined social media–based key quality factors for hospitals. In addition, we developed text mining techniques to detect such factors that frequently occur in online health communities. After detecting these factors that represent qualitative aspects of hospitals, we applied a sentiment analysis to recognize the types of recommendations in messages posted within online health communities. Korea’s two biggest online portals were used to test the effectiveness of detection of social media–based key quality factors for hospitals. Results To evaluate the proposed text mining techniques, we performed manual evaluations on the extraction and classification results, such as hospital name, service quality factors, and recommendation types using a random sample of messages (ie, 5.44% (9450/173,748) of the total messages). Service quality factor detection and hospital name extraction achieved average F1 scores of 91% and 78%, respectively. In terms of recommendation classification, performance (ie, precision) is 78% on average. Extraction and classification performance still has room for improvement, but the extraction results are applicable to more detailed analysis. Further analysis of the extracted information reveals that there are differences in the details of social media–based key quality factors for hospitals according to the regions in Korea, and the patterns of change seem to accurately reflect social events (eg, influenza epidemics). Conclusions These findings could be used to provide timely information to caregivers, hospital officials, and medical officials for health care policies.