Implicit opinion analysis: Extraction and polarity labelling

Huang, Hen-Hsen; Wang, Junjie; Chen, Hsin-Hsi

doi:10.1002/asi.23835

Cited by 5 publications

(3 citation statements)

References 47 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…B and A are the biases of hidden layer D and input layer x, respectively. Due to the limited ability of a single-layer autoencoder to extract signal features, classifiers such as SVM and SoftMax are generally added to the autoencoder [14].…”

Section: 13mentioning

confidence: 99%

Optimizing the Training Mode of Swimmers Based on Deep Learning and Data Mining Technology

Liu

Sun

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Data mining is the most popular research direction of information science nowadays. It revolves around all the data and continuously excavates some of the potentially valuable data information. This information has great application value. This is a dynamic and interactive process. Deep learning is an important branch of machine learning, and the introduction of deep learning theory has promoted the development of artificial intelligence. Swimming is a rather special sport. From the perspective of special characteristics, the body is in an unstable state during swimming, there is no fixed fulcrum, and it is necessary to fight against water resistance in the water. In the case of maintaining the best streamlined and reducing resistance as much as possible, through the power forward movement method brought by rowing and kicking, the training of swimming-specific strength is also unique to the project. In this study, the application of deep learning and data mining technology to the optimization of swimming athletes’ training mode is proposed, and algorithms such as neural network and support vector machine are expounded. This paper adopts two different training methods. That is, the experimental group adopts functional training. The control group used traditional training to compare the special performance of the two groups of athletes before and after physical training. In this way, we can understand the changes of traditional training and functional training on the performance of swimmers, compare the methods of the two groups of athletes and provide swimmers with more scientific and effective training methods. The experimental results of this paper show that through the data mining technology experiment, the main item test scores of the two groups of subjects before and after the experiment were p = 0.004 , which was less than 0.01, showing a very significant difference. This shows that the use of deep learning and data mining technology has a very significant effect on swimming athletes in training to improve performance.

show abstract

Section: 13mentioning

confidence: 99%

Optimizing the Training Mode of Swimmers Based on Deep Learning and Data Mining Technology

Liu

Sun

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…In later work, Deng and Wiebe [27] detected implicitly expressed opinions by implicature inference over explicit sentiment expressions related to events affecting entities. In Chinese, Huang et al [28] annotated a corpus of hotel review snippets and clauses for positive and negative polarity. Recently, the SMP2019-ECISA (https://www.biendata.xyz/competition/smpecisa2019/ (accessed on 7 September 2021)) shared task for Chinese implicit sentiment in social media and car product and tourism forum posts based on Liao et al [7] has spurred new research in implicit polarity modeling.…”

Section: Implicit Sentimentmentioning

confidence: 99%

Fine-Grained Implicit Sentiment in Financial News: Uncovering Hidden Bulls and Bears

Jacobs

Hoste

2021

Electronics

View full text Add to dashboard Cite

The field of sentiment analysis is currently dominated by the detection of attitudes in lexically explicit texts such as user reviews and social media posts. In objective text genres such as economic news, indirect expressions of sentiment are common. Here, a positive or negative attitude toward an entity must be inferred from connotational or real-world knowledge. To capture all expressions of subjectivity, a need exists for fine-grained resources and approaches for implicit sentiment analysis. We present the SENTiVENT corpus of English business news that contains token-level annotations for target spans, polar spans, and implicit polarity (positive, negative, or neutral investor sentiment, respectively). We both directly annotate polar expressions and induce them from existing schema-based event annotations to obtain event-implied implicit sentiment tuples. This results in a large dataset of 12,400 sentiment–target tuples in 288 fully annotated articles. We validate the created resource with an inter-annotator agreement study and a series of coarse- to fine-grained supervised deep-representation-learning experiments. Agreement scores show that our annotations are of substantial quality. The coarse-grained experiments involve classifying the positive, negative, and neutral polarity of known polar expressions and, in clause-based experiments, the detection of positive, negative, neutral, and no-polarity clauses. The gold coarse-grained experiments obtain decent performance (76% accuracy and 63% macro-F1) and clause-based detection shows decreased performance (65% accuracy and 57% macro-F1) with the confusion of neutral and no-polarity. The coarse-grained results demonstrate the feasibility of implicit polarity classification as operationalized in our dataset. In the fine-grained experiments, we apply the grid tagging scheme unified model for <polar span, target span, polarity> triplet extraction, which obtains state-of-the-art performance on explicit sentiment in user reviews. We observe a drop in performance on our implicit sentiment corpus compared to the explicit benchmark (22% vs. 76% F1). We find that the current models for explicit sentiment are not directly portable to our implicit task: the larger lexical variety within implicit opinion expressions causes lexical data scarcity. We identify common errors and discuss several recommendations for implicit fine-grained sentiment analysis. Data and source code are available.

show abstract

“…Studies have found that multi-feature classifiers perform better than single-feature one [9], and hybrid methods perform better than single one [9,24]. Recently, deep learning methods such as convolutional neural network and word-embedding outperformed traditional classification algorithm in the extraction of opinion words [25] and protein–protein interactions [26]. However, the major limitation of supervised method is the cost of data annotation.…”

Section: Literature Reviewmentioning

confidence: 99%

Mining layered technological information in scientific papers: A semi-supervised method

Wang

Zhai

Lin

et al. 2018

Journal of Information Science

View full text Add to dashboard Cite

Tech mining is the application of text mining tools to science and technology information resources. The ever-increasing volume of scientific outputs is a boom to technological innovation, but it also complicates efforts to obtain useful and concise information for problem solving. This challenge extends to tech mining, where the development of techniques compatible with big data is an urgent issue. This article introduces a semi-supervised method for extracting layered technological information from scientific papers in order to extend the reach of tech mining. Our method starts with several pre-set seed patterns used to extract candidate phrases by matching the dependency tree of each sentence. Then, after a series of judgements, phrases are divided into two categories: ‘main technique’ and ‘tech-component’. (A technique, for the purposes of this study, is a method or tool used in the article being analysed.) In order to generate new patterns for subsequent iterations, a weighted pattern learning method is also adopted. Finally, multiple iterations of the method are applied to extract technological information from each paper. A dataset from the field of optical switcher is used to verify the method’s effectiveness. Our findings are that (1) by two loops of extraction process in each iteration, our method realises the layered technological information extraction, which contains the ‘part–whole’ relationships between main techniques and tech-components; (2) the recall rate for main techniques is superior to the baseline after iterating 23 rounds; (3) when layering is disregarded, in the aspect of the precision and the volume of techniques, the new method is higher than that for the baseline; and (4) adjusting another two parameters can optimise the efficiency – however, the effect is neither pronounced nor straightforward.

show abstract

Implicit opinion analysis: Extraction and polarity labelling

Cited by 5 publications

References 47 publications

Optimizing the Training Mode of Swimmers Based on Deep Learning and Data Mining Technology

Optimizing the Training Mode of Swimmers Based on Deep Learning and Data Mining Technology

Fine-Grained Implicit Sentiment in Financial News: Uncovering Hidden Bulls and Bears

Mining layered technological information in scientific papers: A semi-supervised method

Contact Info

Product

Resources

About