<scp>DataChat</scp>: Prototyping a Conversational Agent for Dataset Search and Visualization

Fan, Lizhou; Lafia, Sara; Li, Lingyao; Yang, Fangyuan; Hemphill, Libby

doi:10.1002/pra2.820

Cited by 5 publications

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

When data sharing is an answer and when (often) it is not: Acknowledging data‐driven, non‐data, and data‐decentered cultures

Huvila,

Sinnamon

2024

Asso for Info Science & Tech

View full text Add to dashboard Cite

Contemporary research and innovation policies and advocates of data‐intensive research paradigms continue to urge increased sharing of research data. Such paradigms are underpinned by a pro‐data, normative data culture that has become dominant in the contemporary discourse. Earlier research on research data sharing has directed little attention to its alternatives as more than a deficit. The present study aims to provide insights into researchers' perspectives, rationales and practices of (non‐)sharing of research data in relation to their research practices. We address two research questions, (RQ1) what underpinning patterns can be identified in researchers' (non‐)sharing of research data, and (RQ2) how are attitudes and data‐sharing linked to researchers' general practices of conducting their research. We identify and describe data‐decentered culture and non‐data culture as alternatives and parallels to the data‐driven culture, and describe researchers de‐inscriptions of how they resist and appropriate predominant notions of data in their data practices by problematizing the notion of data, asserting exceptions to the general case of data sharing, and resisting or opting out from data sharing.

show abstract

When data sharing is an answer and when (often) it is not: Acknowledging data‐driven, non‐data, and data‐decentered cultures

Huvila,

Sinnamon

2024

Asso for Info Science & Tech

View full text Add to dashboard Cite

show abstract

Integration patterns in the use of metadata for data sense‐making during relevance evaluation: An interpretable deep learning‐based prediction

Li,

Wang,

Liu

et al. 2024

Asso for Info Science & Tech

View full text Add to dashboard Cite

Integrating diverse cues from metadata to make sense of retrieved data during relevance evaluation is a crucial yet challenging task for data searchers. However, this integrative task remains underexplored, impeding the development of effective strategies to address metadata's shortcomings in supporting this task. To address this issue, this study proposes the “Integrative Use of Metadata for Data Sense‐Making” (IUM‐DSM) model. This model provides an initial framework for understanding the integrative tasks performed by data searchers, focusing on their integration patterns and associated challenges. Experimental data were analyzed using an interpretable deep learning‐based prediction approach to validate this model. The findings offer preliminary support for the model, revealing that data searchers engage in integrative tasks to utilize metadata effectively for data sense‐making during relevance evaluation. They construct coherent mental representations of retrieved data by integrating systematic and heuristic cues from metadata through two distinct patterns: within‐category integration and across‐category integration. This study identifies key challenges: within‐category integration entails comparing, classifying, and connecting systematic or heuristic cues, while across‐category integration necessitates considerable effort to integrate cues from both categories. To support these integrative tasks, this study proposes strategies for mitigating these challenges by optimizing metadata layouts and developing intelligent data retrieval systems.

show abstract

Coconut Libtool: Bridging Textual Analysis Gaps for Non‐Programmers

Santosa,

Lamba,

George

et al. 2024

Proceedings of the Association for Information Science and Tech

View full text Add to dashboard Cite

In the era of big and ubiquitous data, professionals and students alike are finding themselves needing to perform a number of textual analysis tasks. Historically, the general lack of statistical expertise and programming skills has stopped many with humanities or social sciences backgrounds from performing and fully benefiting from such analyses. Thus, we introduce Coconut Libtool (www.coconut-libtool.com/), an open‐source, web‐based application that utilizes state‐of‐the‐art natural language processing (NLP) technologies. Coconut Libtool analyzes text data from customized files and bibliographic databases such as Web of Science, Scopus, and Lens. Users can verify which functions can be performed with the data they have. Coconut Libtool deploys multiple algorithmic NLP techniques at the backend, including topic modeling (LDA, Biterm, and BERTopic algorithms), network graph visualization, keyword lemmatization, and sunburst visualization. Coconut Libtool is the people‐first web application designed to be used by professionals, researchers, and students in the information sciences, digital humanities, and computational social sciences domains to promote transparency, reproducibility, accessibility, reciprocity, and responsibility in research practices.

show abstract

DataChat: Prototyping a Conversational Agent for Dataset Search and Visualization

Cited by 5 publications

References 24 publications

When data sharing is an answer and when (often) it is not: Acknowledging data‐driven, non‐data, and data‐decentered cultures

When data sharing is an answer and when (often) it is not: Acknowledging data‐driven, non‐data, and data‐decentered cultures

Integration patterns in the use of metadata for data sense‐making during relevance evaluation: An interpretable deep learning‐based prediction

Coconut Libtool: Bridging Textual Analysis Gaps for Non‐Programmers

Contact Info

Product

Resources

About