Text analysis using deep neural networks in digital humanities and information science

Suissa, Omri; Elmalech, Avshalom; Zhitomirsky‐Geffet, Maayan

doi:10.1002/asi.24544

Cited by 30 publications

(13 citation statements)

References 79 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, these transformations can be particularly tricky with data in the humanities. The domains of humanities research are highly specialized, so ML algorithms likewise require specialized training data or adaptations to work effectively in them (Suissa et al, 2022). Yet the benefits of doing so are considerable.…”

Section: Humanities and Language Artsmentioning

confidence: 99%

Artificial Intelligence and the Disruption of Higher Education: Strategies for Integrations across Disciplines

Hutson¹,

Jeevanjee²,

Graaf³

et al. 2022

View full text Add to dashboard Cite

Artificial intelligence (AI) and its impact on society have received a great deal of attention in the past five years since the first Stanford AI100 report. AI already globally impacts individuals in critical and personal ways, and many industries will continue to experience disruptions as the full algorithmic effects are understood. Higher education is one of the industries that will be greatly impacted; consequently, many institutions have begun accelerating its adoption across disciplines to address the fast-approaching market shift. Recent advances with the technology are especially promising for its potential to create and scale personalized learning for students, to optimize strategies for learning outcomes, and to increase access to a more diverse populations. In the US alone, colleges are predicted to witness a 48% growth in AI market between 2018-2022. Research has confirmed that the current use of AI in education (AIEd) leads to positive outcomes, including improved learning outcomes for students, along with increased access, increased retention, lower cost of education, and decreased time to completion. Future uses of AI will include the following: enabling engaging and interactive education anytime and anywhere; personalized AI mentors that will help students identify and reach their goals;

show abstract

Section: Humanities and Language Artsmentioning

confidence: 99%

Artificial Intelligence and the Disruption of Higher Education: Strategies for Integrations across Disciplines

Hutson¹,

Jeevanjee²,

Graaf³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Determining what is important, and how to process the important reports quickly, is the most challenging aspect of the analyst's task. A possible solution to enhance paragraph processing is to use innovative capabilities of text analysis (see, e.g., Chen et al, 2012 ; Suissa et al, 2022 ) or through semantic processing instead of simple standalone keywords, by exploiting open‐source software such as UK Defence Science and Technology Laboratory's Baleen (which is freely available from: https://github.com/dstl/baleen3 ). The latter is an extensible text processing capability that allows entity‐related information to be extracted from unstructured and semi‐structured data sources.…”

Section: Discussionmentioning

confidence: 99%

Analysis of noise and bias errors in intelligence information systems

Labib

Chakhar

Hope

et al. 2022

Asso for Info Science & Tech

View full text Add to dashboard Cite

An intelligence information system (IIS) is a particular kind of information systems (IS) devoted to the analysis of intelligence relevant to national security. Professional and military intelligence analysts play a key role in this, but their judgments can be inconsistent, mainly due to noise and bias. The team‐oriented aspects of the intelligence analysis process complicates the situation further. To enable analysts to achieve better judgments, the authors designed, implemented, and validated an innovative IIS for analyzing UK Military Signals Intelligence (SIGINT) data. The developed tool, the Team Information Decision Engine (TIDE), relies on an innovative preference learning method along with an aggregation procedure that permits combining scores by individual analysts into aggregated scores. This paper reports on a series of validation trials in which the performance of individual and team‐oriented analysts was accessed with respect to their effectiveness and efficiency. Results show that the use of the developed tool enhanced the effectiveness and efficiency of intelligence analysis process at both individual and team levels.

show abstract

“…In recent years, DNNs have become the state-of-the-art method for text analysis in the cultural heritage space [111], and natural language question-answering systems based on DNN have become the state-of-the-art method for solving the question answering task [62]. The underlying task of question answering is Machine Reading Comprehension (MRC), which allows machines to read and comprehend a specified context passage for answering a question, similarly to language proficiency exams.…”

Section: Question Answering Using Dnnmentioning

confidence: 99%

Question answering with deep neural networks for semi-structured heterogeneous genealogical knowledge graphs

Suissa

Zhitomirsky‐Geffet

Elmalech

2022

Self Cite

View full text Add to dashboard Cite

With the rising popularity of user-generated genealogical family trees, new genealogical information systems have been developed. State-of-the-art natural question answering algorithms use deep neural network (DNN) architecture based on self-attention networks. However, some of these models use sequence-based inputs and are not suitable to work with graph-based structure, while graph-based DNN models rely on high levels of comprehensiveness of knowledge graphs that is nonexistent in the genealogical domain. Moreover, these supervised DNN models require training datasets that are absent in the genealogical domain. This study proposes an end-to-end approach for question answering using genealogical family trees by: (1) representing genealogical data as knowledge graphs, (2) converting them to texts, (3) combining them with unstructured texts, and (4) training a transformer-based question answering model. To evaluate the need for a dedicated approach, a comparison between the fine-tuned model (Uncle-BERT) trained on the auto-generated genealogical dataset and state-of-the-art question-answering models was performed. The findings indicate that there are significant differences between answering genealogical questions and open-domain questions. Moreover, the proposed methodology reduces complexity while increasing accuracy and may have practical implications for genealogical research and real-world projects, making genealogical data accessible to experts as well as the general public.

show abstract

Text analysis using deep neural networks in digital humanities and information science

Cited by 30 publications

References 79 publications

Artificial Intelligence and the Disruption of Higher Education: Strategies for Integrations across Disciplines

Artificial Intelligence and the Disruption of Higher Education: Strategies for Integrations across Disciplines

Analysis of noise and bias errors in intelligence information systems

Question answering with deep neural networks for semi-structured heterogeneous genealogical knowledge graphs

Contact Info

Product

Resources

About