A domain keyword analysis approach extending Term Frequency-Keyword Active Index with Google Word2Vec model

Hu, Kai; Wu, Huayi; Qi, Kunlun; Yu, Jingmin; Yang, Siluo; Yu, Tianxing; Zheng, Jie; Liu, Bo

doi:10.1007/s11192-017-2574-9

Cited by 77 publications

(54 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Simultaneously, the deep learning model, Word2vec, was used to vectorize the emotional words, followed by the vectorization of the sentences where the emotional words were located. Because Word2vec can capture the contextual information of emotional words in a microblog corpus [ 68 ], the emotional word vector and sentence vector trained by Word2vec can better express the semantic information of texts, thereby improving the performance of identifying the emotions of netizens. Table 2 presents the algorithm for classifying the event-related microblog texts into seven-element emotions.…”

Section: Methodsmentioning

confidence: 99%

Identifying critical outbreak time window of controversial events based on sentiment analysis

Wang

Zhang

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

The response of netizens toward controversial events plays an important guiding role in the development of events. Based on the identification of such responses, this study aimed to determine the critical outbreak time window of events. The microblog texts related to an event were divided into seven emotional categories via multi-emotional analysis to capture the subtle emotions of netizens toward an event, i.e., public opinion. By detecting the characteristics of the text and regional coverage of emotions, an emotional coverage index that reflects the intensity of emotional impact was proposed to determine the mainstream emotion of netizens. By capturing the mutation characteristics of the impact intensity of mainstream emotions, the critical time window of the public opinion toward the event was obtained. The experimental results demonstrated that the proposed method can effectively identify the critical outbreak time window of controversial events, which can help authorities in preventing the further aggravation of events.

show abstract

Section: Methodsmentioning

confidence: 99%

Identifying critical outbreak time window of controversial events based on sentiment analysis

Wang

Zhang

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Die beschriebenen Analysen von häufigen Schlüsselbegriffen können genutzt werden, um Wissensgebiete zu strukturieren und bestehende Trends darzustellen. Im Gegensatz dazu können schwache Signale beziehungsweise niederfrequente Schlüsselbegriffe schon in der Phase der Entstehung auf neue technologische Entwicklungstrends hindeuten . Zur Vorbereitung auf die Zukunft ist es daher wichtig, mögliche schwache Signale aufzufangen und diese darüber hinaus auch kontinuierlich zu verfolgen .…”

Section: Instrumentelle Methodenunclassified

Methoden zur Technologie‐Vorausschau

Möckel¹,

Schumacher

Hake³

2019

Chemie in nserer Zeit

View full text Add to dashboard Cite

show abstract

“…Word2vec was also employed in 2013 as an efficient tool for Google to express words as real-valued vectors. Kai et al [ 7 ]. argued that the domain knowledge is reflected by the semantic meanings behind keywords rather than the keywords themselves.…”

Section: Methodsmentioning

confidence: 99%

A Bayesian Failure Prediction Network Based on Text Sequence Mining and Clustering

Chang

Meng

et al. 2018

Entropy

View full text Add to dashboard Cite

The purpose of this paper is to predict failures based on textual sequence data. The current failure prediction is mainly based on structured data. However, there are many unstructured data in aircraft maintenance. The failure mentioned here refers to failure types, such as transmitter failure and signal failure, which are classified by the clustering algorithm based on the failure text. For the failure text, this paper uses the natural language processing technology. Firstly, segmentation and the removal of stop words for Chinese failure text data is performed. The study applies the word2vec moving distance model to obtain the failure occurrence sequence for failure texts collected in a fixed period of time. According to the distance, a clustering algorithm is used to obtain a typical number of fault types. Secondly, the failure occurrence sequence is mined using sequence mining algorithms, such as-PrefixSpan. Finally, the above failure sequence is used to train the Bayesian failure network model. The final experimental results show that the Bayesian failure network has higher accuracy for failure prediction.

show abstract

A domain keyword analysis approach extending Term Frequency-Keyword Active Index with Google Word2Vec model

Cited by 77 publications

References 15 publications

Identifying critical outbreak time window of controversial events based on sentiment analysis

Identifying critical outbreak time window of controversial events based on sentiment analysis

Methoden zur Technologie‐Vorausschau

A Bayesian Failure Prediction Network Based on Text Sequence Mining and Clustering

Contact Info

Product

Resources

About