Mining for interactive identification of users’ information needs

Liu, Rey-Long; Lin, Wan-Jung

doi:10.1016/s0306-4379(02)00100-x

Cited by 11 publications

(7 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human‐machine interaction (Schumaker, & Chen, ) is another approach to address the feature sparseness of short queries. Liu and Lin () construct and maintain a profile for each information category, and propose an effective method of interacting with the users to map users’ information needs expressed by a short query to suitable categories.…”

Section: Related Workmentioning

confidence: 99%

An evaluation of classification models for question topic categorization

Cong

et al. 2012

Acta Anaesthesiol Scand

View full text Add to dashboard Cite

We study the problem of question topic classification using a very large real-world Community Question Answering (CQA) dataset from Yahoo! Answers. The dataset comprises 3.9 million questions and these questions are organized into more than 1,000 categories in a hierarchy. To the best knowledge, this is the first systematic evaluation of the performance of different classification methods on question topic classification as well as short texts. Specifically, we empirically evaluate the following in classifying questions into CQA categories: (a) the usefulness of n-gram features and bag-of-word features; (b) the performance of three standard classification algorithms (naive Bayes, maximum entropy, and support vector machines); (c) the performance of the state-of-the-art hierarchical classification algorithms; (d) the effect of training data size on performance; and (e) the effectiveness of the different components of CQA data, including subject, content, asker, and the best answer. The experimental results show what aspects are important for question topic classification in terms of both effectiveness and efficiency. We believe that the experimental findings from this study will be useful in real-world classification problems.

show abstract

Section: Related Workmentioning

confidence: 99%

An evaluation of classification models for question topic categorization

Cong

et al. 2012

Acta Anaesthesiol Scand

View full text Add to dashboard Cite

show abstract

“…On one hand, it requires many interactions between a user and the system to identify the appropriate information category (topic) and hence imposes heavy cognitive load on the user. 25 The information agent approach discussed in this paper tries to deal with a more challenging issue in the sense that an information agent should be able to learn appropriate domain specific knowledge (i.e. the retrieval context) with minimal human intervention.…”

Section: Related Workmentioning

confidence: 99%

Sequential Pattern Mining and Nonmonotonic Reasoning for Intelligent Information Agents

Lau

et al. 2007

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

With the explosive growth of information available on the Internet, more effective data mining and data reasoning mechanism is required to process the sheer volume of information. Belief revision logic offers the expressive power to represent information retrieval contexts, and it also provides a sound inference mechanism to model the nonmonotonicity arising in changing retrieval contexts. Contextual knowledge for information retrieval can be extracted via efficient sequential pattern mining. We present a pattern taxonomy extraction model which efficiently performs the task of discovering descriptive frequent sequential patterns by pruning the noisy associations. This paper illustrates a novel approach of integrating the sequential data mining method into the belief revision based adaptive information agents to improve the agents' learning autonomy and prediction power. Initial experiments show that our belief revision logic and sequential pattern mining based intelligent information agents outperform the vector space model based information agents. Our work opens the door to the development of next generation of intelligent information agents to alleviate the information overload problem.

show abstract

“…COD), which are parts of the semantic contents embedded in documents and categories. There were also studies employing COD recognition to classify queries into most-possible categories [6]. However, the classifiers did not consider DF.…”

Section: Related Workmentioning

confidence: 99%

“…To achieve the mission, previous CODbased classifiers (e.g. [6]) require significant modifications, due to two reasons: (1) previous COD recognition techniques is not suitable for performing DF, since a document may be classified into a category only if its COD matches the category's context at each level of generality (rather than considering the average matching degree at multiple levels, as done by previous COD-based classifiers whose goal was to perform DC by identifying the most possible category for the document), and (2) previous thresholding techniques cannot be suitable for the classifiers to derive COD thresholds, since a category's COD threshold should be tuned by considering both the category and ancestors of the category (rather than considering the category only, as done by previous thresholding techniques).…”

Section: Related Workmentioning

confidence: 99%

Mining for context recognition in document filtering and classification

Liu

2005

Fourth Annual ACIS International Conference on Computer and Information Science (ICIS'05)

View full text Add to dashboard Cite

Much information has been hierarchically organized to facilitate information browsing, retrieval, and dissemination. In practice, much information may be entered at any time, but only a small subset of the information may be classified into some categories in a hierarchy. Therefore, achieving document filtering (DF) in the course of document classification (DC) is an essential basis to develop an information center, which classifies suitable documents into suitable categories, reducing information overload while facilitating information sharing. In this paper, we present a technique ICenter, which conducts DF and DC by recognizing the context of discussion (COD) of each document and category. Experiments on realworld data show that, through COD recognition, the performance of ICenter is significantly better. The results are of theoretical and practical significance. ICenter may serve as an essential basis to develop an information center for a user community, which shares and organizes a hierarchy of textual information.

show abstract

Mining for interactive identification of users’ information needs

Cited by 11 publications

References 19 publications

An evaluation of classification models for question topic categorization

An evaluation of classification models for question topic categorization

Sequential Pattern Mining and Nonmonotonic Reasoning for Intelligent Information Agents

Mining for context recognition in document filtering and classification

Contact Info

Product

Resources

About