Investigating the document structure as a source of evidence for multimedia fragment retrieval

Multimedia objects can be retrieved using their context that can be for instance the text surrounding them in documents. This text may be either near or far from the searched objects. Our goal in this paper is to study the impact, in term of effectiveness, of text position relatively to searched objects. The multimedia objects we consider are described in structured documents such as XML ones. The document structure is therefore exploited to provide this text position in documents. Although structural information has been shown to be an effective source of evidence in textual information retrieval, only a few works investigated its interest in multimedia retrieval. More precisely, the task we are interested in this paper is to retrieve multimedia fragments (i.e. XML elements having at least one multimedia object). Our general approach is built on two steps: we first retrieve XML elements containing multimedia objects, and we then explore the surrounding information to retrieve relevant multimedia fragments. In both cases, we study the impact of the surrounding information using the documents structure.     

Using language models to improve opinion detection

Opinion mining is one of the most important research tasks in the information retrieval research community. With the huge volume of opinionated data available on the Web, approaches must be developed to differentiate opinion from fact. In this paper, we present a lexicon-based approach for opinion retrieval. Generally, opinion retrieval consists of two stages: relevance to the query and opinion detection. In our work, we focus on the second state which itself focusses on detecting opinionated documents . We compare the document to be analyzed with opinionated sources that contain subjective information. We hypothesize that a document with a strong similarity to opinionated sources is more likely to be opinionated itself. Typical lexicon-based approaches treat and choose their opinion sources according to their test collection, then calculate the opinion score based on the frequency of subjective terms in the document. In our work, we use different open opinion collections without any specific treatment and consider them as a reference collection. We then use language models to determine opinion scores. The analysis document and reference collection are represented by different language models (i.e., Dirichlet, Jelinek-Mercer and two-stage models). These language models are generally used in information retrieval to represent the relationship between documents and queries. However, in our study, we modify these language models to represent opinionated documents. We carry out several experiments using Text REtrieval Conference (TREC) Blogs 06 as our analysis collection and Internet Movie Data Bases (IMDB), Multi-Perspective Question Answering (MPQA) and CHESLY as our reference collection. To improve opinion detection, we study the impact of using different language models to represent the document and reference collection alongside different combinations of opinion and retrieval scores. We then use this data to deduce the best opinion detection models. Using the best models, our approach improves on the best baseline of TREC Blog (baseline4) by 30%.     

支持虚拟学习环境情境时空维度的用户研究

随着可用的无线移动设备的不断增长,人们对信息检索的需求也越来越大。基于时间的调度服务和基于坐标的定位服务被视为情境感知应用的两个基本点。目前,基于时间的情境感知服务已经应用较多,但存在不能个性化测量等问题。基于坐标的定位服务能否成为常用的基于时间服务系统的替代方法？基于时间和空间维度的RSS信息检索小应用程序的用户研究显示：两种应用程序都有助于接收信息、支持学生组织自己的学习,但是在个人空间中不论基于空间的服务还是基于时间的服务,效果均不突出,而且位置信息被视作不太适宜的环境信息。