How to Develop Reliable Instruments to Measure the Cultural Evolution of Preferences and Feelings in History?

Frontiers in Psychology, Год журнала: 2022, Номер 13

Опубликована: Июль 18, 2022

While we cannot directly measure the psychological preferences of individuals, and moral, emotional, cognitive tendencies people from past, can use cultural artifacts as a window to zeitgeist societies in particular historical periods. At present, an increasing number digitized texts spanning several centuries is available for computerized analysis. In addition, developments form economics have enabled increasingly precise estimations sociodemographic realities past. Crossing these datasets offer powerful tool test how environment changes psychology vice versa . However, designing appropriate proxies relevant constructs not trivial. The gold standard modern – Linguistic Inquiry Word Count (LIWC) has been validated by psychometric experimentation with participants. investigate LIWC limited two main aspects: (1) it does cover entire range dimensions (2) meaning, spelling, pragmatic certain words depend on period which fiction work sampled. These limitations make design custom tools inevitable. without validation, there uncertainty regarding what exactly being measured. To overcome pitfalls, suggest internal external validation procedures, be conducted prior diachronic analyses. First, semantic adequacy search terms bags-of-words approaches should verified training vector spaces text corpus using like word2vec. Second, propose factor analyses evaluate consistency between distinct bag-of-words proxying same underlying construct. Third, externally knowledge differences genres or other literary dimensions. Finally, while analysis documents, used sanity check measures. This procedure allows robust estimation they change throughout history. Together economics, also increases our power testing relationship environmental expression traits

Язык: Английский

---

A Framework for Knowledge Representation Integrated with Dynamic Network Analysis

Lecture notes in networks and systems, Год журнала: 2024, Номер unknown, С. 35 - 49

Опубликована: Янв. 1, 2024

Язык: Английский

---

Intelligent generation method of emergency plan for hydraulic engineering based on knowledge graph – take the South-to-North Water Diversion Project as an example

LHB, Год журнала: 2022, Номер 108(1)

Опубликована: Дек. 31, 2022

There are some problems with the traditional emergency plans of hydraulic engineering, such as low digitisation, poor knowledge relevance, insufficient intelligent decision-making, and so on. This paper proposes an method for generating engineering plan patrol text based on graph machine learning. Firstly, electronic documents various plans, is constructed to realise high organisation scattered knowledge, using skills modelling, extraction, fusion, storage. Then, bidirectional encoder representation from transformers (BERT) long-short-term memory conditional random fields (BiLSTM+CRF), entity recognition model intelligently recognise dangers, projects, parts, other entities in text. The Jaccard similarity algorithm word2vec matches danger generates through retrieval reasoning. With performance verification "Channel Leakage" example, this has accuracy identifying (the F1 value 96.21%) reliability generation which can be applied rescue engineering.

Язык: Английский

---

Characteristics of the knowledge graph of scientific and technological innovation in Gansu Province

Environment Development and Sustainability, Год журнала: 2023, Номер 26(4), С. 10827 - 10843

Опубликована: Март 16, 2023

Язык: Английский

---

A probabilistic ensemble approach for knowledge graph embedding

Neurocomputing, Год журнала: 2022, Номер 500, С. 1041 - 1051

Опубликована: Июнь 8, 2022

Язык: Английский

---