scholarly journals Automatic Deception Detection using Multiple Speech and Language Communicative Descriptors in Dialogs

2021 ◽  
Vol 10 ◽  
Author(s):  
Huang-Cheng Chou ◽  
Yi-Wen Liu ◽  
Chi-Chun Lee
Keyword(s):  
Domain Knowledge ◽  
Deception Detection ◽  
Temporal Dynamics ◽  
Human Life ◽  
Acoustic Features ◽  
Textual Information ◽  
Behavior Understanding ◽  
Proposed Model ◽  
Deceptive Behavior ◽  
Textual Features

While deceptive behaviors are a natural part of human life, it is well known that human is generally bad at detecting deception. In this study, we present an automatic deception detection framework by comprehensively integrating prior domain knowledge in deceptive behavior understanding. Specifically, we compute acoustics, textual information, implicatures with non-verbal behaviors, and conversational temporal dynamics for improving automatic deception detection in dialogs. The proposed model reaches start-of-the-art performance on the Daily Deceptive Dialogues corpus of Mandarin (DDDM) database, 80.61% unweighted accuracy recall in deception recognition. In the further analyses, we reveal that (i) the deceivers’ deception behaviors can be observed from the interrogators’ behaviors in the conversational temporal dynamics features and (ii) some of the acoustic features (e.g. loudness and MFCC) and textual features are significant and effective indicators to detect deception behaviors.

Semi-Supervised Aspect-Based Sentiment Analysis for Case-Related Microblog Reviews Using Case Knowledge Graph Embedding

2021 ◽  
pp. 2050012
Author(s):  
Peilian Zhao ◽  
Cunli Mao ◽  
Zhengtao Yu
Keyword(s):  
Sentiment Analysis ◽  
Domain Knowledge ◽  
Opinion Mining ◽  
Data Augmentation ◽  
Training Data ◽  
Knowledge Graph ◽  
Fine Grained ◽  
Learning Framework ◽  
Proposed Model ◽  
Real World Applications

Aspect-Based Sentiment Analysis (ABSA), a fine-grained task of opinion mining, which aims to extract sentiment of specific target from text, is an important task in many real-world applications, especially in the legal field. Therefore, in this paper, we study the problem of limitation of labeled training data required and ignorance of in-domain knowledge representation for End-to-End Aspect-Based Sentiment Analysis (E2E-ABSA) in legal field. We proposed a new method under deep learning framework, named Semi-ETEKGs, which applied E2E framework using knowledge graph (KG) embedding in legal field after data augmentation (DA). Specifically, we pre-trained the BERT embedding and in-domain KG embedding for unlabeled data and labeled data with case elements after DA, and then we put two embeddings into the E2E framework to classify the polarity of target-entity. Finally, we built a case-related dataset based on a popular benchmark for ABSA to prove the efficiency of Semi-ETEKGs, and experiments on case-related dataset from microblog comments show that our proposed model outperforms the other compared methods significantly.

scholarly journals Local Blood Supply Chain Optimization: A Case Study

2020 ◽  
Vol 18 (4) ◽  
Author(s):  
Reza Babazadeh ◽  
Ali Sabbaghnia ◽  
Fatemeh Shafipour
Keyword(s):  
Supply Chain ◽  
Blood Supply ◽  
Blood Donation ◽  
Programming Model ◽  
Human Life ◽  
Mixed Integer ◽  
Model Parameters ◽  
Supply Chain Optimization ◽  
Blood Supply Chain ◽  
Proposed Model

: Blood and its products play an undeniable role in human life. In recent years, although both academics and practitioners have investigated blood-related problems, further enhancement is still warranted. In this study, a mixed-integer linear programming model was proposed for local blood supply chain management. A supply network, including temporary and fixed blood donation facilities, blood banks, and blood processing centers, was designed regarding the deteriorating nature of blood. The proposed model was applied in a real case in Urmia, Iran. The numerical results and sensitivity analysis of the key model parameters ensured the applicability of the proposed model.

Multi-Criteria Decision Support System for Green Commercial Space Design

2018 ◽  
Vol 43 (4) ◽  
pp. 5-15
Author(s):  
Hao-Cheng Huang ◽  
Yeng-Horng Perng
Keyword(s):  
Decision Support ◽  
Decision Support System ◽  
Energy Saving ◽  
Support System ◽  
Human Life ◽  
Evaluation Model ◽  
High Energy ◽  
Commercial Space ◽  
Proposed Model ◽  
Commercial Spaces

Commercial space features essential characteristics of attracting clients and creating profits; thus, the exterior and interior designs of conventional commercial space were often made to look grandiose and overdecorated. Over time, according to commercial attributes, operator preferences, and style of the designer, commercial spaces have constantly undergone renovation into varied styles. However, the physical renovation processhas caused multiple and composite types of environmental pollution, such as waste and noise pollution caused by breaking of walls or partitions, anddecorative paint pollution, as well as the use of high-energy-consuming lighting equipment, air-conditioning systems, and decorative materials. Global pollution has caused climate change, endangering living organismsand human life. Furthermore, no effective method exists to control the problem of high greenhouse gas emissions. Therefore, this study used energy-saving design concerns of a garden-type commercial space to propose an energy-saving evaluation model. The study combined three methodologies, the Delphi method, analytic hierarchy process, and fuzzy logic theory, to construct a multi-criteria decision support system for designing green commercial spaces, and used the green spatial design of a garden café as an example to illustrate the high objectivity and adaptability of the proposed model in practical application. The study also used an international award-winning case to validate that the proposed model had practical value as a reference to support key design decisions.

scholarly journals Learning Phenotypes and Dynamic Patient Representations via RNN Regularized Collective Non-Negative Tensor Factorization

2019 ◽  
Vol 33 ◽  
pp. 1246-1253 ◽  
Author(s):  
Kejing Yin ◽  
Dong Qian ◽  
William K. Cheung ◽  
Benjamin C. M. Fung ◽  
Jonathan Poon
Keyword(s):  
Temporal Dynamics ◽  
Mortality Prediction ◽  
Temporal Data ◽  
Tensor Factorization ◽  
Observation Window ◽  
Health Records ◽  
Disease States ◽  
Clinical Events ◽  
Proposed Model ◽  
Mimic Iii

Non-negative Tensor Factorization (NTF) has been shown effective to discover clinically relevant and interpretable phenotypes from Electronic Health Records (EHR). Existing NTF based computational phenotyping models aggregate data over the observation window, resulting in the learned phenotypes being mixtures of disease states appearing at different times. We argue that by separating the clinical events happening at different times in the input tensor, the temporal dynamics and the disease progression within the observation window could be modeled and the learned phenotypes will correspond to more specific disease states. Yet how to construct the tensor for data samples with different temporal lengths and properly capture the temporal relationship specific to each individual data sample remains an open challenge. In this paper, we propose a novel Collective Non-negative Tensor Factorization (CNTF) model where each patient is represented by a temporal tensor, and all of the temporal tensors are factorized collectively with the phenotype definitions being shared across all patients. The proposed CNTF model is also flexible to incorporate non-temporal data modality and RNN-based temporal regularization. We validate the proposed model using MIMIC-III dataset, and the empirical results show that the learned phenotypes are clinically interpretable. Moreover, the proposed CNTF model outperforms the state-of-the-art computational phenotyping models for the mortality prediction task.

scholarly journals Evaluating forest fire probability under the influence of human activity based on remote sensing and GIS

2020 ◽  
Author(s):  
Wei Yang ◽  
Xiaoli Jiang
Keyword(s):  
Remote Sensing ◽  
Forest Fire ◽  
Human Life ◽  
Remote Sensing Data ◽  
Anthropogenic Factors ◽  
Operating Characteristics ◽  
Distance Analysis ◽  
Comprehensive Method ◽  
Proposed Model ◽  
Probability Prediction

Abstract. Fires are an important factor involved in the disturbance of forest ecosystems, causing resource damage and the loss of human life. Evaluating forest fire probability can provide an effective method to minimize these losses. In this study, a comprehensive method that integrates remote-sensing data and geographic information systems is proposed to evaluate forest fire probability. In our analysis, we selected four probability indicators: drought index, vegetation condition, topographical factors and anthropogenic factors. To evaluate the influence of anthropogenic factors on fire probability, a distance analysis from fire locations to settlements or roads was conducted to see which distance was associated with a higher probability. The forest fire probability index (FFPI) was calculated to assess the probability level in Heilongjiang Province, China. According to the FFPI, five classes were identified: very low, low, moderate, high, and very high. A receiver operating characteristics (ROC) curve was used as the validation method, and the results of the ROC analysis showed that the proposed model performed well in terms of forest fire probability prediction. The results of this study provide a technical framework for the Department of Forest Resource Management to predict occurrence of fires.

A domain knowledge graph construction method based on Wikipedia

2020 ◽  
pp. 016555152093251
Author(s):  
Haoze Yu ◽  
Haisheng Li ◽  
Dianhui Mao ◽  
Qiang Cai
Keyword(s):  
Domain Knowledge ◽  
Multiple Scale ◽  
Construction Method ◽  
Knowledge Graph ◽  
Relationship Extraction ◽  
Proposed Model ◽  
Extraction Algorithm ◽  
Structured Knowledge ◽  
Extraction Model ◽  
Domain Independent

In order to achieve real-time updating of the domain knowledge graph and improve the relationship extraction ability in the construction process, a domain knowledge graph construction method is proposed. Based on the structured knowledge in Wikipedia’s classification system, we acquire concepts and instances contained in subject areas. A relationship extraction algorithm based on co-word analysis is intended to extract the classification relationships in semi-structured open labels. A Bi-GRU remote supervised relationship extraction model based on a multiple-scale attention mechanism and an improved cross-entropy loss function is proposed to obtain the non-classification relationships of concepts in unstructured texts. Experiments show that the proposed model performs better than the existing methods. Based on the obtained concepts, instances and relationships, a domain knowledge graph is constructed and the domain-independent nodes and relationships contained in them are removed through a vector variance algorithm. The effectiveness of the proposed method is verified by constructing a food domain knowledge graph based on Wikipedia.

scholarly journals Estimating Latent People Flow without Tracking Individuals

2018 ◽  
Author(s):  
Yusuke Tanaka ◽  
Tomoharu Iwata ◽  
Takeshi Kurashima ◽  
Hiroyuki Toda ◽  
Naonori Ueda
Keyword(s):  
New York ◽  
New York City ◽  
Real World ◽  
Diffusion Processes ◽  
Temporal Dynamics ◽  
Location Information ◽  
Aggregated Data ◽  
Proposed Model ◽  
Real World Datasets ◽  
Flow Conservation

Analyzing people flows is important for better navigation and location-based advertising. Since the location information of people is often aggregated for protecting privacy, it is not straightforward to estimate transition populations between locations from aggregated data. Here, aggregated data are incoming and outgoing people counts at each location; they do not contain tracking information of individuals. This paper proposes a probabilistic model for estimating unobserved transition populations between locations from only aggregated data. With the proposed model, temporal dynamics of people flows are assumed to be probabilistic diffusion processes over a network, where nodes are locations and edges are paths between locations. By maximizing the likelihood with flow conservation constraints that incorporate travel duration distributions between locations, our model can robustly estimate transition populations between locations. The statistically significant improvement of our model is demonstrated using real-world datasets of pedestrian data in exhibition halls, bike trip data and taxi trip data in New York City.

scholarly journals Abstractive Text Summary of COVID-19 Documents based on LSTM Method and Word Embedding

Webology ◽  
2021 ◽  
Vol 18 (2) ◽  
pp. 1011-1022
Author(s):  
Saja Naeem Turky ◽  
Ahmed Sabah Ahmed AL-Jumaili ◽  
Rajaa K. Hasoun
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
Input Sequence ◽  
Word Embedding ◽  
Suggested Model ◽  
Specific Domain ◽  
Scientific Texts ◽  
Proposed Model ◽  
Pass Through ◽  
Single Statement

An abstractive summary is a process of producing a brief and coherent summary that contains the original text's main concepts. In scientific texts, summarization has generally been restricted to extractive techniques. Abstractive methods that use deep learning have proven very effective in summarizing articles in public fields, like news documents. Because of the difficulty of the neural frameworks for learning specific domain- knowledge especially in NLP task, they haven't been more applied to documents that are related to a particular domain such as the medical domain. In this study, an abstractive summary is proposed. The proposed system is applied to the COVID-19 dataset which a collection of science documents linked to the coronavirus and associated illnesses, in this work 12000 samples from this dataset have been used. The suggested model is an abstractive summary model that can read abstracts of Covid-19 papers then create summaries in the style of a single-statement headline. A text summary model has been designed based on the LSTM method architecture. The proposed model includes using a glove model for word embedding which is converts input sequence to vector forms, then these vectors pass through LSTM layers to produce the summary. The results indicate that using an LSTM and glove model for word embedding together improves the summarization system's performance. This system was evaluated by rouge metrics and it achieved (43.6, 36.7, 43.6) for Rouge-1, Rouge-2, and Rouge-L respectively.

scholarly journals SELF-EQUALITY AS A STRATEGY OF SPONTANEOUS TEXT GENERATION

2017 ◽  
pp. 184-190
Author(s):  
G. G. Moskaltchuk
Keyword(s):  
Computer Program ◽  
Human Life ◽  
The Self ◽  
Thought Processes ◽  
Text Generation ◽  
Textual Information ◽  
Finite Integral ◽  
Special Computer Program ◽  
Text Formation ◽  
Spontaneous Reaction

The article deals with the results of the psycholinguistic experiment which prove the influence of the self-equality strategy in the process of spontaneous reaction text generation as a reaction on the stimulus “human life”. The materials have been analyzed with the help of a special computer program which marks the reaction texts parameters: text size in words (from space to space) and in sentences as well as the text formula reflecting the finite integral state of the whole. It has been found out that the self-equality as the principle of structuring speech forming activity is also used when producing reaction texts. The form reflects the hidden laws of the text synergetics and its synchronization with the speech-thought processes of the human acting with lack of time, it shows the hidden laws of the text formation. The probability of the realization of the 7 dominant models of the text form in the experiment is 824 texts of 1 thousand, in the directed one – 705 texts. The text formats reflect the discretization of the inner textual information. The average text size in the free experiment is 27.82 words, in sentences – 2.64, in the directed experiment – 12.34 and 6.79 sentences correspondingly. The reaction texts set on one page are formed by the tested according to a selected pattern and have hardly any stylistic, graphic and punctuation difference. The forms generated in the process of experiment are more end-oriented with attractors located in the end alongside with the dominant sense.

Sign in / Sign up

Export Citation Format

Share Document