Talk in Eye Movements Workshop, Grenoble

This last Friday (June, 8th) I presented at the Grenoble Workshop on Models and Analysis of Eye Movements our framework for a Multimodal Analysis of Teaching Centered on Shared Attention and Knowledge Access, co-authored with Louise Héléna Aubineau, Dominique Vaufreydaz, and Jim Crowley. The abstract is below, and there are the [Slides].

The effects of teaching on learning are mostly uncertain, hidden, and not immediate. Research investigating how teaching can have an impact on learning has recently been given a significant boost with signal processing devices and data mining analyses. We devised a framework for the study of teaching and learning processes which posits that lessons are composed of episodes of joint attention and access to the taught content, and that the interplay of behaviors like joint attention, actional contingency, and feedback loops compose different levels of teaching. Teaching by social tolerance, which occurs when learners (Ls) have no attentional problems but their access to the taught knowledge depends on the teacher (T). Teaching by opportunity provisioning, when Ls can be aware on the taught content but lack access to it (e.g., lack of understanding), and T builds ad hoc situations in which Ls are provided with easier content. Teaching by stimulus or local enhancement, when Ls have fully access to the content but lack attention toward it. T explicitly shows content to Ls, slows down her behaviors, tells and acts in an adapted way (e.g., motherese). A variety of devices installed in a classroom will capture and automatically characterize these events. T’s and Ls’ utterances and gazes will be recorded through low-cost cameras installed on 3D printed glasses, and T will wear a mobile eye tracker and a mobile microphone. Instructional material is equipped with qrcodes so that Ls’ and T’s video streams are processed to determine where people are looking at, and to infer the corresponding teaching levels. This novel framework will be used to analyze instructional events in ecological situations, and will be a first step to build a ?pervasive classroom?, where eye-tracking and sensor-based devices analyze a wide range of events in a multimodal and interdisciplinary way.

Gutu and Paraschiv PhD Thesis Committees

On Thursday 28th, Nov., I’ll be attending the PhD thesis committee of two students from University ‘Politehnica’ of Bucharest, Gabriel Gutu and Ionut Paraschiv, supervised by Stefan Trausan-Matu.
Gabriel Gutu‘s thesis is entitled “Discourse Analysis based on Semantic Modelling and Textual Complexity” and aims at extending some ReaderBench‘s functionalities in the domain of CSCL discussion analysis.
Ionut Paraschiv’s thesis (Semantic Meta-Annotation and Comprehension Modeling) also adds features to ReaderBench, in comprehension modeling and scientometrics.
For more information, read below their summaries.

Gabriel Gutu thesis’ summary

The exponential growth of digital documents, together with the necessity for analysis and extraction of valuable information within them, bring routine work for people. The opportunity for development of automated discourse analysis services and techniques leads to automation of laborious operations. In the long run, the transferring of tiresome operations into computerized systems would allow people to focus on “high level” assignments that lead to interesting ideas and provide the means to extract thoughts and understandings that are currently hardly interpreted by computers.
Discourse analysis refers to the extraction of relevant information from documents by using techniques of analysis known in scientific literature as Natural Language Processing. The services presented in this thesis make use of recent advancements in the field by integrating semantic models and textual complexity factors. Semantic models allow the mapping of documents into mathematical representations that provide comparison and scoring for units of texts, be them either simple words, sentences, paragraphs or even entire documents. Of the semantic models, the thesis relies on Latent Semantic Analysis, Latent Dirichlet Allocation and the more recent Word2vec. The WordNet ontology is the lexicon used as alternative to semantic models. Compared to semantic models, a lexicon expresses “more natural” relations between units of texts because of relying on a dictionary and using relations between words that are created in collaboration with linguists.
The experiments were performed by extending ReaderBench, a multi-lingual Natural Language Processing open-source framework. Two directions were followed: 1) analysis of Computer Supported Collaborative Learning (CSCL) chat conversations; 2) automation of processes of discourse analysis through mechanisms adaptable to various scenarios relying on textual content. The studies performed on CSCL conversations targeted the idea of developing an automated mechanism of detection of implicit links, facility that is missing in chat platforms. By integrating such a mechanism, the outlined relations between utterances may ease processes like detection of topics, voices or lexical chains. The researches performed on documents included automated classification of documents, assessment of documents’ quality or automated scoring of students’ assignments in a Massive Open Online Course platform. The mechanisms were validated on real world data extracted. Services were exposed through an Application Programming Interface.
The author of this thesis beliefs that the presented experiments could provide ideas for future studies and could ease the involved work by allowing researchers to focus on their topics while relying on the validated mechanisms by using the implemented services made available through the open-source ReaderBench framework.

Ionut Paraschiv thesis’ summary

Each domain, alongside its knowledge base, changes over time and each period is centered on specific topics that emerge from different ongoing research projects. A researcher’s daily activities usually involve the study of new papers and using the information for building solutions and observing how the domain evolves. Since the retrieval of documents from the Internet can lead to large data flows, it is important to consider other approaches for a more comprehensive analysis of the domain. In this context, the Semantic Meta Annotations focus on building a scalable paper annotation system that automatically retrieves papers on a given topic and tags them, to make the exploration phase of the research literature substantially easier.
Evolution is based on leveraging existing knowledge, researches and tools to test other ideas. A researcher needs to read many textual materials, which are many times cluttered with irrelevant information. Thus, the focus of our research is shifted towards understanding the way in which humans comprehend texts. Reading is a complex cognitive process which has been the subject of many studies throughout the years. It is one of the oldest ways for learners to acquire new information and to consolidate existing knowledge, representing a key evolutionary element. Each textual material contains facts and topics that activate existing concepts from the reader’s prior knowledge (memory). The Comprehension Model describes an automated method that analyzes the way in which readers potentially assimilate and conceptualize new text information, which is a novel alternative for indexing and meta-annotating textual corpora. Creating such a method is a challenge, as it requires using a computational knowledge base, parsing unstructured textual materials and linking concepts using various heuristics and semantic similarity measures.
Our research focuses on the semantic analysis of unstructured textual materials by using Natural Language Processing techniques and models such as Latent Semantic Analysis, Latent Dirichlet Allocation, Word2Vec or semantic distances within lexicalized ontologies, i.e., WordNet. Within the experiments focused on semantic meta annotations, these distances are combined with other metrics such as co-citation analysis or co-authorship, thus creating the basis of several interactive and exploratory visual graphs that offer a better domain overview within a scalable infrastructure. In the second experiment, our focus is shifted towards describing an automatic comprehension modelling technique that analyzes using computational representations and algorithms the reading process. Our goal was to create a set of methods and tools to help researchers in their daily work to easily retrieve and understand textual materials.

EC-TEL 2017

We’ll have three pieces of work to be presented in EC-TEL 2017 in Tallinn, Estonia, on 12-15 Sept.

First of all, a demo of ReaderBench, the system I’m working on, in collaboration with Mihai Dascalu, Stefan Trausan-Matu and their team of UPB (Romania), as well as Danielle McNamara (Arizona State Univ.) and Scott Crossley (Georgia State Univ.), with a focus on the textual complexity features of the system.

Secondly, a poster introducing to Semantic Boogle, a Boogle-based game for learning vocabulary which populates the grid with semantically-related words from a given stem (and relying on ReaderBench).

Thirdly, a full paper (written with Laurent Thuez, from the nurse training institute of Annecy-Genevois, France, Mihai Dascalu, and Stefan Trausan-Matu ) aiming at automatically analyzing a set of nurse students case studies. We wondered to what extent some indices from a large series of complexity measures can predict the human assessment of these case studies.

Thesis: Analyzing Text Complexity and Timeline Evolution

On next Monday, the 26th of September, I will be in the PhD Thesis defence committee of Lucia Larise Stavarache. She designed “BlogCrawl” on top of ReaderBench, which allows to automatically harvest forums and chats, to be in turn analyzed by ReaderBench in terms of knowledge building and participation. Below is an excerpt of her thesis.

The approach underneath this thesis explores and integrates advanced Computer Supported Collaborative Learning, Natural Language Processing techniques and Learning Communities research in a consolidated view of how knowledge emerges from supervised and alternative educational environments. Furthermore, extending the dimensional space of analysis through time, topics and sentiments, this thesis presents a multi-dimensional analysis on the evolution of learning communities. Going one step further, the findings resulted are then crossed analyzed from a tutor student relationship in order to fill the current gaps and converge to a collaborative educational approaches inspired by the work of Bakhtin (Bakhtin, 1981) Vykostki (Vygotsky, 1978), Scardamalia (Scardamalia, 2002) and Stahl (Stahl, Koschmann, & Suthers, 2006).
The committee is composed of Nic Nistor, Florin Radulescu, Stefan Trausan-Matu (supervisor), and myself.

Teacher’s Sensitivity towards pupils: a Mobile Eye Tracking Study

Just presented, yesterday the 14th of September, at EC-TEL conf. (in Lyon), a study aiming at investigating which cues teachers detect and process from their students during instruction. This information capturing process depends on teachers’ sensitivity, or awareness, to students’ needs, which has been recognized as crucial for classroom management.

We recorded the gaze behaviors of two pre-service teachers and two experienced teachers during a whole math lesson in primary classrooms. Thanks to a simple Learning Analytics interface, the data analysis reports, firstly, which were the most often tracked students, in relation with their classroom behavior and performance; secondly, which relationships exist between teachers’ attentional frequency distribution and lability, and the overall classroom climate they promote, measured by the Classroom Assessment Scoring System. Results show that participants’ gaze patterns are mainly related to their experience. Learning Analytics use cases are eventually presented, enabling researchers or teacher trainers to further explore the eye-tracking data.
The co-authors of this study are: Olivier Cosnefroy, LSE, Univ. Grenoble Alpes & Vanda Luengo, LIP6, UPMC, Paris.
The full paper is available here.

ReaderBench: Automated Evaluation of Collaboration

Just published in the Int J CSCL a paper entitled “ReaderBench: Automated evaluation of collaboration based on cohesion and dialogism”. This paper introduces to our recent experiments testing ReaderBench to assess its CSCL-based features.

As Computer-Supported Collaborative Learning (CSCL) gains a broader usage, the need for automated tools capable of supporting tutors in the time-consuming process of analyzing conversations becomes more pressing. Moreover, collaboration, which presumes the intertwining of ideas or points of view among participants, is a central element of dialogue performed in CSCL environments. Therefore, starting from dialogism and a cohesion-based model of discourse, we propose and validate two computational models for assessing collaboration. The first model is based on a cohesion graph and can be perceived as a longitudinal analysis of the ongoing conversation, thus accounting for collaboration from a social knowledge-building perspective. In the second approach, collaboration is regarded from a dialogical perspective as the intertwining or synergy of voices pertaining to different speakers, therefore enabling a transversal analysis of subsequent discussion slices.

[Article]

Natural cognitive foundations of teacher knowledge

Just published Natural cognitive foundations of teacher knowledge, co-authored with Franck Tanguy and André Tricot, has just been published by a Sense Publishers book edited by Michel Grangeat.

The aim of this paper is to explore a cognitive way to define teachers’ professional knowledge (TPK), arguing that some ‘natural’ knowledge, stemming from several human social abilities – and, for many of them, animal – is thus engaged in teaching as well. The actions grounded on such knowledge are undertaken automatically or at a low cognitive load due to the nature of the latter.
Some theoretical views on teaching include such an assumption (Csibra, 2007; Csibra & Gergely, 2011; Strauss, 2005; Strauss & Ziv, 2012), but so far, little research has investigated teachers’ cognitive processes in relation to both natural cognition and Cognitive Load Theory (CLT) (see however Feldon, 2007; Moos & Pitton, 2013).
This paper seeks firstly to consider teachers’ actions through the lens of natural cognition and pedagogy, then to set up a framework for teacher cognition and knowledge, showing that several social abilities and knowledge can be used for teaching purposes, and with a low cognitive load. Then, we describe the abilities for teaching as primary vs. secondary knowledge. Eventually, we use this framework to assess or predict which cognitive load is in relation with teachers’ performances according to the CLASS, a renowned classroom observation system.
[link to the whole book]