Costin-Gabriel Chiru

Automatic assessment of collaborative chat conversations with PolyCAFe

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 collaborative chat conversations and discussion forums. The architecture of the system is presented by focusing on two key components: the assessment of the utterances and of the collaborative discourse. PolyCAFes effectiveness has been proved in a validation experiment with students and tutors from a University course. The main findings from this trial, together with the conclusions of domain experts verifying the accuracy of the assessment provided by PolyCAFe, are also analyzed and commented in detail.

Overview and preliminary results of using polyCAFe for collaboration analysis and feedback generation

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.

Identification and classification of the most important moments from students' collaborative discourses

In this paper we present a method that combines the cognitive and socio-cultural paradigms for automatically identifying the most important moments (the so-called pivotal moments) from a Computer Supported Collaborative Learning chat. The existing applications do not identify these moments and we propose a flexible visual method for filling this gap. Since these moments may have different roles in a discourse, we also propose a classification of the identified types of important moments from chat conversations.

Detecting and Describing Historical Periods in a Large Corpora

Many historic periods (or events) are remembered by slogans, expressions or words that are strongly linked to them. Educated people are also able to determine whether a particular word or expression is related to a specific period in human history. The present paper aims to establish correlations between significant historic periods (or events) and the texts written in that period. In order to achieve this, we have developed a system that automatically links words (and topics discovered using Latent Dirichlet Allocation) to periods of time in the recent history. For this analysis to be relevant and conclusive, it must be undertaken on a representative set of texts written throughout history. To this end, instead of relying on manually selected texts, the Google Books Ngram corpus has been chosen as a basis for the analysis. Although it provides only word n-gram statistics for the texts written in a given year, the resulting time series can be used to provide insights about the most important periods and events in recent history, by automatically linking them with specific keywords or even LDA topics.

Cost efficient cloud-based service oriented architecture for water pollution prediction

River water quality nowadays represents a major concern. Performing water monitoring, in order to detect the pollutant with wireless sensor networks is not enough. Furthermore, the solution to place more sensors for monitoring is not cost efficient as this type of sensors are very expensive. In the case of a pollution accident on a river, it is mandatory to alert people and, more important, to predict the evolution of pollutant concentration, downstream. Also, it is essential to minimize the time-frame to send the alert to the possibly affected people. In this paper, we propose a cost-efficient cloud-based service oriented architecture for water pollution prediction and alert system. The cost efficiency of our approach comes from the three main directions. The first way is represented by the usage of less water monitoring specific sensors due to the usage of complex hydraulic models. The second direction is represented by the construction of a knowledge-base with pre-run scenarios of pollution propagation events. The third direction is represented by the usage of cloud computing services which are proven to be cost effective. The novelty of our approach comes from the integration of different Cloud computing platforms and services, in order achieve scalability, provisioning of resources in real time, to have a simplified deployment and management of resources and applications, and to get a better cost/performance ratio.

Repetition and rhythmicity based assessment model for chat conversations

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 Bakhtins polyphony theory and Tannens 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.

Time Series Analysis for Sales Prediction

In this paper, we present an approach to forecasting the number of paintings that will be sold daily by Vivre Deco S.A. Vivre is an online retailer for Home and Lifestyle in Central and Eastern Europe. One of its concerns is related to the stocks that it needs to make at its own warehouse (considering its limited available space) to ensure a good product flow that would maximize both the company profit and the users’ satisfaction. Since stocks are directly connected to sales, the purpose is to predict the amount of sales from each category of products, given the selling history of these products. Thus, we have chosen a category of products (paintings) and used ARIMA for obtaining the predictions. We present different considerations regarding how we chose the model, along with the solver and the optimization method for fitting ARIMA. We also discuss the influence of the differencing on the obtained results, along with information about the runtime of different models.

Expression of Political Opinions in Press

In this paper, we present an application designed to analyze news articles from Romanian mass media and extract opinions about political entities relevant to the major political stage. The application was created with the desire to study media polarization around important political events, such as legislative or presidential elections. The application uses different crawlers to extract the data from online newspapers and save it in the database. Then, it uses several Machine Learning techniques for identifying and classifying opinions about given entities over a long span of time. Based on this classification, it generates reports and charts that could be use not only to study political polarization, but also to identify partisan media.

Profiling of Participants in Chat Conversations Using Creativity-Based Heuristics.

This article proposes a new fully automated method for identifying creativity that is manifested in a divergent task. The task is represented by chat conversations in small groups, each group having to debate on the same topics, with the purpose of better understanding the discussed concepts. The chat conversations were created by undergraduate students in computer science studying human-computer interaction in several consecutive years. From this corpus of conversations, the chats from a single year were selected for analysis. These 25 chats contained 8,798 utterance, made of 82,176 word appearances with a vocabulary size of 5,948 distinct words. By analyzing the resulted dataset of chat conversations, the creative ideas expressed by participants are automatically identified and extracted. The application is a first step in supporting creativity in online group discussions by highlighting the novel concepts present in conversations (new ideas) and also by identifying topics that could have become important, but they were forgotten during the debates (lost ideas). Once the ideas are identified, the system tries to also capture their developments, the reactions they attract and the conclusions that are drawn based on them. Because group constituency might influence the level of creative discourse within a conversation, the typology of each participant to the conversation is evaluated, starting from the analysis of the ideas already discovered, along with the utterances labeled as developments, reactions and conclusions.

Hearthstone Helper - Using Optical Character Recognition Techniques for Cards Detection

In this paper we address the problem of capturing, processing and analyzing images from the video stream of the Hearthstone game in order to obtain relevant information on the conduct of parties in this game. Since the information needs to be presented to the user in real-time, we needed to find the most suitable methods of extracting this information. Therefore, techniques such as background subtraction, histograms comparisons, key points matching, optical character recognition were investigated. Driven by the required processing speed, we ended up using optical character recognition on limited areas of interest from the captured image. After developing the application, we tested it in real-world context, while real games were played and presented the obtained results. In the end, we also provided two examples where the application would prove useful for better decision making during the game.