Costin Chiru

Word sense disambiguation is an essential, yet a very difficult task in natural language processing. While several other NLP tasks, such as POS tagging, can provide more than fairly good results (highly accurate, with almost 100% rate of successfully labeled words), disambiguation is far from achieving such performances. However, we will demonstrate the need of word sense disambiguation in computing the lexical chains on a special kind of text (chats) using a WordNet-based approach. In addition, we will try to identify the bottlenecks (mostly in respect to accuracy) in such an approach and provide possible improvements.

The wider acceptance and usage of instant messaging (chat) represents one of the consequences of undertaking Computer-Supported Collaborative Learning (CSCL) practices in formal education settings. However, the difficulty of analyzing these textual artifacts of learners in order to offer them feedback represents a serious problem in further extending the usage of chat conversations. PolyCAFe is a system that was designed to support the tutors and to provide automatic feedback for the learners engaged in ...

This report is about the way to deliver relevant feedback to students' written production, either for free texts (eg, essays, syntheses, notes) or chat conversation, in order for the students to build knowledge. This report presents an overview and a selection of existing models, methods and resources for: 1) the automatic analysis of learner interactions using language technologies or social network analysis (Task 5.1) and 2) the automatic analysis of learner text (Task 5.2). Secondly, a proposition of the tools to be developed for the project ...

This report presents Version 1 of the support and feedback services (delivering recommendations based on interaction analysis and on students' textual production) that can be integrated within an e-learning environment. Further steps toward the implementation of Version 2 of these services and their future integration with all the LTfLL services are also suggested.

The perception of environmental information (EI) and the way that it is structured within Environmental Information Portals (EIP) are of major importance for the design of such information systems. The present paper investigates the concepts of air quality perception and applies natural language processing for developing a framework of concepts, phrases, patterns, collocations, and metaphors around an air quality ontology. The results reveal the frequency of appearance and the relations between basic terms, thus reflecting domain ...

ABSTRACT Starting from the socio-constructivist concepts of (virtual) community of practice (vCoP) and internet-based argumentative open-ended learning environments, this study proposes and validates two tools for automated dialogue assessment, ReaderBench and Important Moments, developed on the ground of the polyphonic social knowledge building model. The analyzed corpus was the dialogue produced by an academic vCoP with N = 179 community members in 23 months, and consisting of 3685 interventions in 292 text-based discussion threads. The analysis results uncovered significant differences in the discussion threads produced by central and peripheral participants, such that central participants produced more interventions with higher collaborative dialogue quality, and the discussion threads they initiated were longer and involved a larger number of participants. Moreover, based on the automated analysis result, the vCoP participants could be classified in two clusters corresponding to the well-known core-periphery structure of CoPs. These findings are consistent with those revealed by other methods, and suggest that the employed tools are appropriate for identifying virtual communities that are appropriate as open-ended learning environments. Further research and development is needed to deepen quantitative vCoP models and test communication strategies recommended to students in vCoP-based argumentative open-ended learning environments.

This paper presents a model and an application that can be used to assess chat conversations according to their content, which is related to a number of imposed topics, and to the personal involvement of the participants. The main theoretical ideas that stand behind this application are Bakhtin’s polyphony theory and Tannen’s ideas related to the use of repetitions. The results of the application are validated against the gold standard provided by two teachers from the Human-Computer Interaction evaluating the same chats and after that the verification is done using another teacher from the same domain. During the verification we also show that the model used for chat evaluation is dependent on the number of participants to that chat.

ABSTRACT Conference code: 81593, Export Date: 16 August 2011, Source: Scopus, Language of Original Document: English, Correspondence Address: Rebedea, T.; Department of Computer Science and Engineering, Politehnica University of Bucharest, 313 Splaiul Independetei, Bucharest, Romania; email: traian.rebedea@cs.pub.ro, References: Adams, P.H., Martell, C.H., Topic detection and extraction in chat (2008) Proceedings of the 2008 IEEE International Conference on Semantic Computing, pp. 581-588;

Although Computer-Supported Collaborative Learning (CSCL) advocates the use of instant messaging and discussion forums for collaboration between learners, there is a scarcity of tools for leveraging the information in this kind of conversations. Thus, these technologies are primarily used for communication and, once the conversation is over, the raw data is rarely manually analyzed by tutors, teachers and other learners. This paper presents a methodology and a system that can be used for providing feedback and support to learners and tutors that are involved in tasks that make use of chats and forums. In order to achieve this objective, PolyCAFe employs Natural Language Processing and Social Network Analysis techniques to discover polyphony and inter-animation in textual collaborations. To evaluate the proposed approach and the designed system a first validation experiment has been performed and the results are discussed and analyzed in the end of the paper.

Abstract Depending on the user's intention, the queries processed by a search engine can be classified in transactional, informational and navigational [1]. In order to meet the three types of searches, at this moment search engines basically use algorithmic analysis of the links between pages improved by a factor that depends on the number of occurrences of the keywords in the query and the order of these words on each web page returned as a result. For transactional and informational queries, the relevance of the results returned by the ...