ReaderBench Talk: Online Conversations Empowered by Advanced NLP Techniques

Andrei Mardale, Gabriel Gutu-Robu, Mihai Dascalu, Stefan Trausan-Matu

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

1 Downloads (Pure)

Abstract

With the increased need of communication, Computer-Supported Collaborative Learning has gained a broader attention within the last years. Thus, the necessity of using chat applications emerged; however, most solutions lack the integration of Natural Language Processing (NLP) services in order to provide support and guidance, while discussing. Our novel application Talk is integrated within the ReaderBench framework and is defined by three main features: asynchronous messages specific to chats, automated bots for enhancing participants’ involvement and interactions, as well as the usage of advanced NLP functionalities for a posteriori evaluations. ReaderBench Talk communicates with the framework through a dedicated endpoint built within the ReaderBench API. As preliminary validation, two assignments were given to students from our faculty. Overall, students were able to solve the tasks without encountering critical bugs and they also provided valuable feedback. Their feedback revealed the usefulness of the application, its ease of use, the persistency of data, and the quality of the NLP services. The feedback also helped identify issues, which were mainly related to the user interface and to the communication with the server.
Original languageEnglish
Title of host publicationIn Conf. Nat. de Interactiune Om-Calculator (RoCHI 2014)
PublisherMATRIX ROM
Pages63-70
Publication statusPublished - 2014
Externally publishedYes
Event15th International Conference on Human Computer Interaction, RoCHI 2018, Cluj-Napoca, Romania - Cluj-Napoca, Romania
Duration: 3 Sep 20184 Sep 2018
http://rochi2018.utcluj.ro/

Conference

Conference15th International Conference on Human Computer Interaction, RoCHI 2018, Cluj-Napoca, Romania
Abbreviated title15th RoCHI 2018
CountryRomania
CityCluj-Napoca
Period3/09/184/09/18
Internet address

Fingerprint

Feedback
Processing
Students
Communication
Application programming interfaces (API)
User interfaces
Servers

Keywords

  • Chat Conversations
  • Computer-Supported Collaborative Learning
  • ReaderBench framework
  • Natural Language Processing
  • Chat Bots

Cite this

Mardale, A., Gutu-Robu, G., Dascalu, M., & Trausan-Matu, S. (2014). ReaderBench Talk: Online Conversations Empowered by Advanced NLP Techniques. In In Conf. Nat. de Interactiune Om-Calculator (RoCHI 2014) (pp. 63-70). MATRIX ROM.
Mardale, Andrei ; Gutu-Robu, Gabriel ; Dascalu, Mihai ; Trausan-Matu, Stefan. / ReaderBench Talk: Online Conversations Empowered by Advanced NLP Techniques. In Conf. Nat. de Interactiune Om-Calculator (RoCHI 2014). MATRIX ROM, 2014. pp. 63-70
@inproceedings{d29756ec5d5a4c6a9f1096fc092b1f06,
title = "ReaderBench Talk: Online Conversations Empowered by Advanced NLP Techniques",
abstract = "With the increased need of communication, Computer-Supported Collaborative Learning has gained a broader attention within the last years. Thus, the necessity of using chat applications emerged; however, most solutions lack the integration of Natural Language Processing (NLP) services in order to provide support and guidance, while discussing. Our novel application Talk is integrated within the ReaderBench framework and is defined by three main features: asynchronous messages specific to chats, automated bots for enhancing participants’ involvement and interactions, as well as the usage of advanced NLP functionalities for a posteriori evaluations. ReaderBench Talk communicates with the framework through a dedicated endpoint built within the ReaderBench API. As preliminary validation, two assignments were given to students from our faculty. Overall, students were able to solve the tasks without encountering critical bugs and they also provided valuable feedback. Their feedback revealed the usefulness of the application, its ease of use, the persistency of data, and the quality of the NLP services. The feedback also helped identify issues, which were mainly related to the user interface and to the communication with the server.",
keywords = "Chat Conversations, Computer-Supported Collaborative Learning, ReaderBench framework, Natural Language Processing, Chat Bots",
author = "Andrei Mardale and Gabriel Gutu-Robu and Mihai Dascalu and Stefan Trausan-Matu",
note = "This publication reflects only the author's view and the European Commission is not responsible for any use that may be made of the information it contains.",
year = "2014",
language = "English",
pages = "63--70",
booktitle = "In Conf. Nat. de Interactiune Om-Calculator (RoCHI 2014)",
publisher = "MATRIX ROM",
address = "Romania",

}

Mardale, A, Gutu-Robu, G, Dascalu, M & Trausan-Matu, S 2014, ReaderBench Talk: Online Conversations Empowered by Advanced NLP Techniques. in In Conf. Nat. de Interactiune Om-Calculator (RoCHI 2014). MATRIX ROM, pp. 63-70, 15th International Conference on Human Computer Interaction, RoCHI 2018, Cluj-Napoca, Romania, Cluj-Napoca, Romania, 3/09/18.

ReaderBench Talk: Online Conversations Empowered by Advanced NLP Techniques. / Mardale, Andrei ; Gutu-Robu, Gabriel ; Dascalu, Mihai; Trausan-Matu, Stefan.

In Conf. Nat. de Interactiune Om-Calculator (RoCHI 2014). MATRIX ROM, 2014. p. 63-70.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

TY - GEN

T1 - ReaderBench Talk: Online Conversations Empowered by Advanced NLP Techniques

AU - Mardale, Andrei

AU - Gutu-Robu, Gabriel

AU - Dascalu, Mihai

AU - Trausan-Matu, Stefan

N1 - This publication reflects only the author's view and the European Commission is not responsible for any use that may be made of the information it contains.

PY - 2014

Y1 - 2014

N2 - With the increased need of communication, Computer-Supported Collaborative Learning has gained a broader attention within the last years. Thus, the necessity of using chat applications emerged; however, most solutions lack the integration of Natural Language Processing (NLP) services in order to provide support and guidance, while discussing. Our novel application Talk is integrated within the ReaderBench framework and is defined by three main features: asynchronous messages specific to chats, automated bots for enhancing participants’ involvement and interactions, as well as the usage of advanced NLP functionalities for a posteriori evaluations. ReaderBench Talk communicates with the framework through a dedicated endpoint built within the ReaderBench API. As preliminary validation, two assignments were given to students from our faculty. Overall, students were able to solve the tasks without encountering critical bugs and they also provided valuable feedback. Their feedback revealed the usefulness of the application, its ease of use, the persistency of data, and the quality of the NLP services. The feedback also helped identify issues, which were mainly related to the user interface and to the communication with the server.

AB - With the increased need of communication, Computer-Supported Collaborative Learning has gained a broader attention within the last years. Thus, the necessity of using chat applications emerged; however, most solutions lack the integration of Natural Language Processing (NLP) services in order to provide support and guidance, while discussing. Our novel application Talk is integrated within the ReaderBench framework and is defined by three main features: asynchronous messages specific to chats, automated bots for enhancing participants’ involvement and interactions, as well as the usage of advanced NLP functionalities for a posteriori evaluations. ReaderBench Talk communicates with the framework through a dedicated endpoint built within the ReaderBench API. As preliminary validation, two assignments were given to students from our faculty. Overall, students were able to solve the tasks without encountering critical bugs and they also provided valuable feedback. Their feedback revealed the usefulness of the application, its ease of use, the persistency of data, and the quality of the NLP services. The feedback also helped identify issues, which were mainly related to the user interface and to the communication with the server.

KW - Chat Conversations

KW - Computer-Supported Collaborative Learning

KW - ReaderBench framework

KW - Natural Language Processing

KW - Chat Bots

M3 - Conference article in proceeding

SP - 63

EP - 70

BT - In Conf. Nat. de Interactiune Om-Calculator (RoCHI 2014)

PB - MATRIX ROM

ER -

Mardale A, Gutu-Robu G, Dascalu M, Trausan-Matu S. ReaderBench Talk: Online Conversations Empowered by Advanced NLP Techniques. In In Conf. Nat. de Interactiune Om-Calculator (RoCHI 2014). MATRIX ROM. 2014. p. 63-70