Teerapong Leelanupab

King Mongkut's Institute of Technology Ladkrabang · Faculty of Information Technology

News has been an important source for many financial time series predictions based on fundamental analysis. However, digesting a massive amount of news and data published on the Internet to predict a market can be burdensome. This article introduces a topic model based on Latent Dirichlet Allocation (LDA) to discover features from a combination of...

Pair-programming is an Agile technique in Extreme Programming (XP) where traditionally two programmers need to be collocated and work together at one workstation. Previous research has shown that pair-programming is very beneficial in software engineering education. However, learning and practicing pair-programming are mostly limited in a class whe...

This paper proposes a new methodology that automatically generates English mnemonic keywords to support the learning of basic Japanese vocabulary. A new phonetic algorithm, called JemSoundex, is also introduced for phonetically transliterating the Japanese and English languages for phonetic matching. The effective mnemonic keywords are selected and...

This paper proposes a new framework to identify and rank Twitter accounts of which short messages or tweets may influence a specific financial stock price. In this paper, we start by mainly focusing on the first step of our framework, selecting potential influencers based on their association with a particular stock market. With numerous limitation...

This paper proposes an approach to generate query suggestions by employing information from user-created visual snippets. In order to generate query suggestions, we apply the optical character recognition (OCR) technique to extract a set of words presented in the visual snippet. The natural language processing (NLP) is used to identify the words th...

To support language learning by using the principle of a Mnemonic technique, this paper proposes to automatically generate suggested mnemonic words by using “phonetic algorithms”, i.e., Soundex and Metaphone. Levenshtein edit distance is employed to compare the phonetic similarity of foreign words and that of words in a known language using the sou...

Thermal feedback provides a novel emotive, private and salient communication channel between human and computer. It could be used as an alternative to or replacement for common notification channels (e.g., visual, vibrotactile and audio feedback) for situations that are too bright, bumpy, and noisy. Until now, little investigation has been conducte...

People often engage in many search tasks that be collaborative, where two or more individuals work together with the joint information needs. We introduced and built CoZpace, a web-based application that enables a group of users to collaborate on searching the web. We also presented the main feature of CoZpace, named Snapboard, which is a shared bo...

This paper proposes a new evaluation metric, normalized Coverage Frequency (nCF), which aims to explicitly evalu- ate the diversity of search results, going beyond the draw- backs of previously proposed measures. In fact, two of the most widely adopted metrics for the diversity retrieval task, namely α-nDCG and Intent-Aware Expected Reciprocal Rank...

In this paper, we propose a new educational system for second-language vocabulary learning based on a mnemonic technique. The system is equipped with the dynamic and interactive interface that allows vocabulary learners to seamlessly browse a collection of foreign words while suggesting phonetically related words of a known lan-guage for helping th...

มีเหตุการณ์จำนวนมากที่เกิดขึ้นในชีวิตประจำวันซึ่งโดยปกติแล้วเราไม่สามารถจดจำได้ทั้งหมด การบันทึกชีวิตประจำวัน (Lifelogging) สามารถช่วยให้เราระลึกถึงเหตุการณ์สำคัญต่างๆได้ โดยสามารถแบ่งออกได้เป็น 2 ประเภทใหญ่ๆ ได้แก่ i) การบันทึกชีวิตโดยมือ (manual) คือ การบันทึกโดยใช้สมุดบันทึกหรือไดอะรี่ และ ii) การบันทึกชีวิตโดยอัตโนมัติ (automatic) คือ การใช้อุป...

Today’s search systems are mainly designed for one user to use individually. Search activities in practice can, however, be conducted by two or more users working together. This is due to the fact that information seeking tasks are complex and often requires multiple users’ efforts to collaboratively assess and search for relevant information. In s...

Language is a method of human communication and essential to express ourselves, e.g., ideas, feelings, thoughts. With an agreement of ten ASEAN nations in 2007, the regional economic integration, also known as the ASEAN Economic Community (AEC), will be established by 2015. In particular, Thailand is currently the largest trading partner of Laos wi...

ผู้คนส่วนใหญ่มักจะนิยมถ่ายภาพเก็บไว้เป็นที่ระลึก หรือบางครั้งก็นำภาพที่ได้มาใช้ในการประชาสัมพันธ์ เมื่อกล่าวถึงการว่าจ้างช่างภาพ หากคนที่เคยว่าจ้างช่างภาพมาก่อนมักไม่ค่อยมีปัญหาในการว่าจ้าง ต่างจากผู้ที่ไม่เคยว่าจ้างช่างภาพมาก่อน เพราะไม่ทราบว่าจะหาช่างภาพจากที่ใดบ้าง ดังนั้นผู้ว่าจ้าง จึงต้องสอบถามจากคนรู้จักที่เคยว่าจ้างช่างภาพมาก่อน เพื่อทราบถึง...

การวิจัยครั้งนี้มีวัตถุประสงค์เพื่อพัฒนาระบบปฏิสัมพันธ์เพื่อช่วยการเรียนรู้ภาษาโดยคอมพิวเตอร์สำหรับสอนภาษาลาวซึ่งเป็นหนึ่งในภาษาอาเซียนที่สำคัญ โดยนำเทคโนโลยีสารสนเทศมาประยุกต์ใช้กับการเรียนภาษาเพื่อเพิ่มประสิทธิภาพและประสิทธิผลในการเรียนรู้ของผู้เรียน รวมทั้งช่วยในการเตรียมความพร้อมด้านภาษาในการเข้าสู่ประชาคมเศรษฐกิจอาเซียนของประเทศไทย ระบบถูกออกแ...

เสิร์ชเอนจิน (Search Engine) ถูกใช้งานเพื่อการค้นหาข้อมูลอย่างแพร่หลาย ระบบการค้นคืนในปัจจุบันถูกออกแบบมาสำหรับการใช้งานสำหรับผู้ใช้เพียงคนเดียว แต่ในงานบางประเภท ผู้ใช้จำเป็นที่จะต้องค้นหาข้อมูลร่วมกันมากกว่าหนึ่งคนหรือร่วมกันเป็นทีม ทั้งนี้เนื่องจากข้อมูลที่ต้องการค้นหานั้นอาจมีเป็นจำนวนมากหรือยากแก่การค้นหาโดยเพียงคนเดียว การที่ผู้ใช้แต่ละคนทำกา...

The massive volume of Twitter data has attracted much attention of researchers to study their correlation with stock market. Tweets with stock symbols can be identified by the prefix with dollar sign or by using some complex techniques. In this paper, we focus on discovering NASDAQ stock symbols in a stream of tweets. We propose a simple but effect...

In the field of information retrieval (IR), researchers and practitioners are often faced with a demand for valid approaches to evaluate the performance of retrieval systems. The Cranfield experiment paradigm has been dominant for the in-vitro evaluation of IR systems. Alternative to this paradigm, laboratory-based user studies have been widely use...

In this paper we define two models of users that require diversity in search results; these models are theoretically grounded in the notion of intrinsic and extrinsic diversity. We then examine Intent-Aware Expected Reciprocal Rank (ERR-IA), one of the official measures used to assess diversity in TREC 2011-12, with respect to the proposed user mod...

Search activities are evolving to new ways and many search activities are conducted collaboratively. This paper introduces the de- velopment and evaluation of a synchronous collaborative web browsing system called CoFox. CoFox provides a platform to allow a pair of users to tackle collaborative search tasks. We introduce the architecture of the sys...

In the TREC Web Diversity track, novelty-biased cumulative gain (α-NDCG) is one of the official measures to assess retrieval performance of IR systems. The measure is characterised by a parameter, α, the effect of which has not been thoroughly investigated. We find that common settings of α, i.e. α=0.5, may prevent the measure from behaving as desi...

Time plays a central role in many web search information needs relating to recent events. For recency queries where fresh information is most desirable, there is likely to be a great deal of highly-relevant information created very recently by crowds of people across the world, particularly on platforms such as Wikipedia and Twitter. With so many u...

Novelty-biased cumulative gain ( -NDCG) has become the de facto measure within the information retrieval (IR) community for evaluating retrieval systems in the context of sub-topic retrieval. Setting the incorrect value of parameter in -NDCG prevents the measure from behaving as desired in particular circumstances. In fact, when is set according to...

The presence of spam in a document ranking is a major issue for Web search engines. Common approaches that cope with spam remove from the document rankings those pages that are likely to contain spam. These approaches are implemented as post-retrieval processes, that filter out spam pages only after documents have been retrieved with respect to a u...

For TREC Crowdsourcing 2011 (Stage 2) we propose a networkbased approach for assigning an indicative measure of worker trustworthiness in crowdsourced labelling tasks. Workers, the gold standard and worker/gold standard agreements are modelled as a network. For the purpose of worker trustworthiness assignment, a variant of the PageRank algorithm, n...

In this paper, we consider the problem of document ranking in a non-traditional retrieval task, called subtopic retrieval. This task involves promoting relevant documents that cover many subtopics of a query at early ranks, providing thus diversity within the ranking. In the past years, several approaches have been proposed to diversify retrieval r...

Ranking documents according to the Probability Ranking Principle has been theoretically shown to guarantee optimal retrieval effectiveness in tasks such as ad hoc document retrieval. This ranking strategy assumes independence among document relevance assessments. This assumption, however, often does not hold, for example in the scenarios where redu...

In this paper, we present a study of adaptive image browsing, based on high-level classification. The underlying hypothesis is that the performance of a browsing model can be improved by integrating high-level semantic concepts. We introduce a multi-label classification model designed to alleviate a binary classification problem in image classifica...

In this paper we describe the approaches adopted to generate the runs submitted to ImageCLEFPhoto 2009 with an aim to promote document diversity in the rankings. Four of our runs are text based approaches that employ textual statistics extracted from the captions of images, i.e. MMR [1] as a state of the art method for result diversification, two a...

In this paper we describe the approaches adopted to generate the five runs submitted to Image Clef Photo 2009 by the University of Glasgow. The aim of our methods is to exploit document diversity in the rankings. All our runs used text statistics extracted from the captions associated to each image in the collection, except one run which combines t...

In this paper, we introduce a novel approach to recommend images by mining user interactions based on implicit feedback of user browsing. The underlying hypothesis is that the interaction implicitly indicates the interests of the users for meeting practical image retrieval tasks. The algorithm mines interaction data and also low-level content of th...

In this paper, we propose a unified architecture for the cre-ation of life-long user profiles. Our architecture combines different steps required for a user profile, including feature extraction and representa-tion, reasoning, recommendation and presentation. We discuss various issues that arise in the context of life-long profiling.

Traditional information retrieval (IR) systems mostly focus on finding documents relevant to queries without considering other documents in the search results. This approach works quite well in general cases; however, this also means that the set of returned documents in a result list can be very similar to each other. This can be an undesired syst...

Pictures are often self-explanatory; they capture a moment in time. However, a single photo cannot represent the whole moment. The creation of photographic stories is a means to better preserve memories. Relying on the content-based and contextual metadata within digital photos we could assist users to explore their collection to create the stories...