Classifying help seeking behaviour in online communities

Cross, Sebastian; Waters, Zak; Kitto, Kirsty; Zuccon, Guido

doi:10.1145/3027385.3027442

Cited by 11 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used three models for detecting the presence of the aforementioned features by consolidating the DQ and IHS detection processes into one model and using an independent model for HSS and HSC. The model for the DQ and IHS features was trained on a publicly available data set [53] to detect the direct and implied questions asked by a user in their status updates. In the given data set, we used the sentences along with their labels as training data for both DQ and IHS features detection.…”

Section: Methodsmentioning

confidence: 99%

Exploring the dominant features of social media for depression detection

Hussain

Satti

Afzal

et al. 2019

Journal of Information Science

View full text Add to dashboard Cite

Recently, social media have been used by researchers to detect depressive symptoms in individuals using linguistic data from users’ posts. In this study, we propose a framework to identify social information as a significant predictor of depression. Using the proposed framework, we develop an application called the Socially Mediated Patient Portal (SMPP), which detects depression-related markers in Facebook users by applying a data-driven approach with machine learning classification techniques. We examined a data set of 4350 users who were evaluated for depression using the Center for Epidemiological Studies Depression (CES-D) scale. From this analysis, we identified a set of features that can distinguish between individuals with and without depression. Finally, we identified the dominant features that adequately assess individuals with and without depression on social media. The model trained on these features will be helpful to physicians in diagnosing mental diseases and psychiatrists in analysing patient behaviour.

show abstract

Section: Methodsmentioning

confidence: 99%

Exploring the dominant features of social media for depression detection

Hussain

Satti

Afzal

et al. 2019

Journal of Information Science

View full text Add to dashboard Cite

show abstract

“…Increasingly, LA tools are being developed to automate this classification process using Machine Learning (ML) (see e.g. [13,29]), and it is common to evaluate these methods by considering how well their classifications overlap with that of human annotators (a point to which we will return shortly). Most of these tools are currently used in a research context, but the aim is to use them in our teaching and learning practice.…”

Section: What Type Of Learning?mentioning

confidence: 99%

Embracing imperfection in learning analytics

Kitto

Gibson

2018

Proceedings of the 8th International Conference on Learning Analytics and Knowledge

Self Cite

View full text Add to dashboard Cite

Learning Analytics (LA) sits at the confluence of many contributing disciplines, which brings the risk of hidden assumptions inherited from those fields. Here, we consider a hidden assumption derived from computer science, namely, that improving computational accuracy in classification is always a worthy goal. We demonstrate that this assumption is unlikely to hold in some important educational contexts, and argue that embracing computational "imperfection" can improve outcomes for those scenarios. Specifically, we show that learner-facing approaches aimed at "learning how to learn" require more holistic validation strategies. We consider what information must be provided in order to reasonably evaluate algorithmic tools in LA, to facilitate transparency and realistic performance comparisons. CCS CONCEPTS • Human-centered computing → User models; • Computing methodologies; • General and reference → Validation;

show abstract

“…Adaptation of existing indicators to new scenarios is required, e.g. for skill modelling [30] or help-seeking behavior [31]. Existing advances in LA, however, do not consider the particular requirements of SLEs with massive number of participants or offering ubiquitous learning opportunities based on IoT or the new requirements that these scenarios pose to interoperability.…”

Section: Learning Analytics For the Design And Orchestration In Slesmentioning

confidence: 99%

“…Moreover, the research community [26,31] and a recent report by the European Commission claim that important research still needs to be done to tailor data analytics towards supporting more meaningful learning design in SLEs as well as a more effective orchestration using data collected and processed during runtime. Some authors state that a tandem between LD and LA offers the opportunity to better interpret the resulting data against the original pedagogical intent and the local context, to evaluate the success of a particular learning activity.…”

Section: Learning Analytics For the Design And Orchestration In Slesmentioning

confidence: 99%

SmartLET

Kloos

Dimitriadis

Hernández‐Leo

et al. 2018

Proceedings of the Sixth International Conference on Technological Ecosystems for Enhancing Multiculturality

View full text Add to dashboard Cite

This paper presents the SmartLET project, a coordinated research project funded by the Spanish Ministry of Science, Innovation and Universities, which just started in 2018. The main aim of this project is to provide support for the design and orchestration of Smart Learning Environments (SLEs) with the support of learning analytics and the Internet of Things. This paper gives an overview of our conception of SLEs based on previous works, provides some ideas about the connection of learning design and orchestration with SLEs, and analyses different ethical and privacy issues for SLEs. In addition, an initial hypothesis and some specific objectives for a support environment for SLEs are proposed.

show abstract

Classifying help seeking behaviour in online communities

Cited by 11 publications

References 18 publications

Exploring the dominant features of social media for depression detection

Exploring the dominant features of social media for depression detection

Embracing imperfection in learning analytics

SmartLET

Contact Info

Product

Resources

About