Citation Context

...ations. Analysis of speech acts for online chat and instant messages and have been studied in computer-mediated communication (CMC) and distance learning (Twitchell et al., 2004; Nastri et al., 2006; =-=Rosé et al., 2008-=-). In natural language processing, Cohen et al. (2004) and Feng et al. (2006) used speech acts to capture the intentional focus of emails and discussion boards. However, they assume that enough labele...

Citation Context

... most content analyses in the CSCL literature have relied on manually coded data as in our own paper [5], it seems clear that automated natural language processing methods (such as those described in =-=[12]-=-) will be more scalable for future analyses. 5i.e., threads which receive no responses 2 would not be able to do alone, collaborative environments effectively form a scaffolding [20] for learners to p...

Citation Context

... the Deep Loop classifiers to identify good and bad discussion situations. 2 Related Work The most relevant work to ours is by Rosé and colleagues, who have developed the text analysis tool TagHelper =-=[3]-=-, also used in our work. Originally, they aimed at freeing corpus analysts from the tedious task of manually coding large amounts of data, rather than analyzing online discussions, which is our goal. ...

Citation Context

...sresults.sRelated WorksAnalyzing student contributions and assigning labels is common practice in designingsand experimenting with intelligent educational technology. For instance, the researchers in =-=[6]-=- investigated machine-learning approaches by training classifiers on the language of a large corpus of labeled data and classifying single contributions into categories. These results led to the devel...

Citation Context

...opulation does not necessarily work well with another population because the use of software and language might differ. Our final issue concerns the unit of analysis. Two of the presented approaches (=-=Rosé et al., 2008-=-; Verbree et al., 2006) rely on pre-segmented data that does not correspond to natural delimitations such as sentence or message boundaries. For instance, each message might contain several “epistemic...

Citation Context

...ators [117], latent growth curves [150], dynamic multilevel analysis [151], event-centred analysis [119]), and uptake contingency graphs [116]. Finally, recent developments in automated coding [152], =-=[153]-=- offer directions for natural language processing applications for CL monitoring and assessment. CL-display 1. Awareness displays. Research on awareness orginated in the area of Computer-Supported Coo...

Citation Context

...enbourg, 2002), where the application of inappropriate or unneeded supports have a detrimental effect on collaboration and learning. Dynamic Script-Based Support with Conversational Agents The early non-adaptive scripting approaches described above can sometimes result in both overscripting and in interference between multiple scripts (Weinberger et al., 2007), both of which have been shown to be detrimental to student performance. More dynamic approaches can trigger scripted support in response to the automatic analysis of participant activity (Soller & Lesgold, 2000; Erkens & Janssen, 2008; Rosé et al., 2008; McLaren et al., 2007; Mu et al., 2012). This sort of analysis can occur at a macro-level, following the state of the activity as a whole, or it can be based on the microlevel classification of individual user contributions. Some prior work on adaptive support for collaborative learning used hint-based support for individual learning with technology to support peer tutoring interactions (Diziol et al., 2010). Other prior work on dynamic conversational agent based support built on a long history of work using tutorial dialogue agents to support individual learning with technology (Wiemer-Hasti...