Semantic frame-based approach for reade-remotion detection

Yung Chun Chang, Cen Chieh Chen, Wen Lian Hsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Previous studies on emotion classification mainly focus on the writer's emotional state. By contrast, this research emphasizes emotion detection from the readers' perspective. The classification of documents into reader-emotion categories can be applied in several ways, and one of the applications is to retain only the documents that trigger desired emotions to enable users to retrieve documents that contain relevant contents and at the same time instill proper emotions. However, current IR systems lack the ability to discern emotions within texts, and the detection of reader-emotion has yet to achieve a comparable performance. Moreover, previous machine learning-based approaches are generally not human understandable. Thereby, it is difficult to pinpoint the reason for recognition failures and understand the types of emotions articles inspire in their readers. In this paper, we propose a flexible semantic frame-based approach (FBA) for reader-emotion detection that simulates such process in a human perceptive manner. FBA is a highly automated process that incorporates various knowledge sources to learn semantic frames from raw text that characterize an emotion and are comprehensible for humans. Generated frames are adopted to predict reader-emotion through an alignment-based matching algorithm that allows a semantic frame to be partially matched through a statistical scoring scheme. Experimental results demonstrate that our approach can effectively detect reader-emotions by exploiting the syntactic structures and semantic associations in the context, while outperforming currently well-known statistical text classification method sand the stat-of-the-art reader-emotion detection method.

Original languageEnglish
Title of host publicationPacific Asia Conference on Information Systems, PACIS 2015 - Proceedings
PublisherPacific Asia Conference on Information Systems
Publication statusPublished - 2015
Externally publishedYes
Event19th Pacific Asia Conference on Information Systems, PACIS 2015 - Singapore, Singapore
Duration: Jul 5 2015Jul 9 2015

Conference

Conference19th Pacific Asia Conference on Information Systems, PACIS 2015
CountrySingapore
CitySingapore
Period7/5/157/9/15

Fingerprint

Semantics
Syntactics
Learning systems
Sand

Keywords

  • Frame-based approach
  • Reader-emotion detection
  • Semantic frame
  • Sentiment analysis.
  • Text classification

ASJC Scopus subject areas

  • Information Systems

Cite this

Chang, Y. C., Chen, C. C., & Hsu, W. L. (2015). Semantic frame-based approach for reade-remotion detection. In Pacific Asia Conference on Information Systems, PACIS 2015 - Proceedings Pacific Asia Conference on Information Systems.

Semantic frame-based approach for reade-remotion detection. / Chang, Yung Chun; Chen, Cen Chieh; Hsu, Wen Lian.

Pacific Asia Conference on Information Systems, PACIS 2015 - Proceedings. Pacific Asia Conference on Information Systems, 2015.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chang, YC, Chen, CC & Hsu, WL 2015, Semantic frame-based approach for reade-remotion detection. in Pacific Asia Conference on Information Systems, PACIS 2015 - Proceedings. Pacific Asia Conference on Information Systems, 19th Pacific Asia Conference on Information Systems, PACIS 2015, Singapore, Singapore, 7/5/15.
Chang YC, Chen CC, Hsu WL. Semantic frame-based approach for reade-remotion detection. In Pacific Asia Conference on Information Systems, PACIS 2015 - Proceedings. Pacific Asia Conference on Information Systems. 2015
Chang, Yung Chun ; Chen, Cen Chieh ; Hsu, Wen Lian. / Semantic frame-based approach for reade-remotion detection. Pacific Asia Conference on Information Systems, PACIS 2015 - Proceedings. Pacific Asia Conference on Information Systems, 2015.
@inproceedings{599f7b938a9643f7908f22b05142dfe3,
title = "Semantic frame-based approach for reade-remotion detection",
abstract = "Previous studies on emotion classification mainly focus on the writer's emotional state. By contrast, this research emphasizes emotion detection from the readers' perspective. The classification of documents into reader-emotion categories can be applied in several ways, and one of the applications is to retain only the documents that trigger desired emotions to enable users to retrieve documents that contain relevant contents and at the same time instill proper emotions. However, current IR systems lack the ability to discern emotions within texts, and the detection of reader-emotion has yet to achieve a comparable performance. Moreover, previous machine learning-based approaches are generally not human understandable. Thereby, it is difficult to pinpoint the reason for recognition failures and understand the types of emotions articles inspire in their readers. In this paper, we propose a flexible semantic frame-based approach (FBA) for reader-emotion detection that simulates such process in a human perceptive manner. FBA is a highly automated process that incorporates various knowledge sources to learn semantic frames from raw text that characterize an emotion and are comprehensible for humans. Generated frames are adopted to predict reader-emotion through an alignment-based matching algorithm that allows a semantic frame to be partially matched through a statistical scoring scheme. Experimental results demonstrate that our approach can effectively detect reader-emotions by exploiting the syntactic structures and semantic associations in the context, while outperforming currently well-known statistical text classification method sand the stat-of-the-art reader-emotion detection method.",
keywords = "Frame-based approach, Reader-emotion detection, Semantic frame, Sentiment analysis., Text classification",
author = "Chang, {Yung Chun} and Chen, {Cen Chieh} and Hsu, {Wen Lian}",
year = "2015",
language = "English",
booktitle = "Pacific Asia Conference on Information Systems, PACIS 2015 - Proceedings",
publisher = "Pacific Asia Conference on Information Systems",

}

TY - GEN

T1 - Semantic frame-based approach for reade-remotion detection

AU - Chang, Yung Chun

AU - Chen, Cen Chieh

AU - Hsu, Wen Lian

PY - 2015

Y1 - 2015

N2 - Previous studies on emotion classification mainly focus on the writer's emotional state. By contrast, this research emphasizes emotion detection from the readers' perspective. The classification of documents into reader-emotion categories can be applied in several ways, and one of the applications is to retain only the documents that trigger desired emotions to enable users to retrieve documents that contain relevant contents and at the same time instill proper emotions. However, current IR systems lack the ability to discern emotions within texts, and the detection of reader-emotion has yet to achieve a comparable performance. Moreover, previous machine learning-based approaches are generally not human understandable. Thereby, it is difficult to pinpoint the reason for recognition failures and understand the types of emotions articles inspire in their readers. In this paper, we propose a flexible semantic frame-based approach (FBA) for reader-emotion detection that simulates such process in a human perceptive manner. FBA is a highly automated process that incorporates various knowledge sources to learn semantic frames from raw text that characterize an emotion and are comprehensible for humans. Generated frames are adopted to predict reader-emotion through an alignment-based matching algorithm that allows a semantic frame to be partially matched through a statistical scoring scheme. Experimental results demonstrate that our approach can effectively detect reader-emotions by exploiting the syntactic structures and semantic associations in the context, while outperforming currently well-known statistical text classification method sand the stat-of-the-art reader-emotion detection method.

AB - Previous studies on emotion classification mainly focus on the writer's emotional state. By contrast, this research emphasizes emotion detection from the readers' perspective. The classification of documents into reader-emotion categories can be applied in several ways, and one of the applications is to retain only the documents that trigger desired emotions to enable users to retrieve documents that contain relevant contents and at the same time instill proper emotions. However, current IR systems lack the ability to discern emotions within texts, and the detection of reader-emotion has yet to achieve a comparable performance. Moreover, previous machine learning-based approaches are generally not human understandable. Thereby, it is difficult to pinpoint the reason for recognition failures and understand the types of emotions articles inspire in their readers. In this paper, we propose a flexible semantic frame-based approach (FBA) for reader-emotion detection that simulates such process in a human perceptive manner. FBA is a highly automated process that incorporates various knowledge sources to learn semantic frames from raw text that characterize an emotion and are comprehensible for humans. Generated frames are adopted to predict reader-emotion through an alignment-based matching algorithm that allows a semantic frame to be partially matched through a statistical scoring scheme. Experimental results demonstrate that our approach can effectively detect reader-emotions by exploiting the syntactic structures and semantic associations in the context, while outperforming currently well-known statistical text classification method sand the stat-of-the-art reader-emotion detection method.

KW - Frame-based approach

KW - Reader-emotion detection

KW - Semantic frame

KW - Sentiment analysis.

KW - Text classification

UR - http://www.scopus.com/inward/record.url?scp=85011072154&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011072154&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85011072154

BT - Pacific Asia Conference on Information Systems, PACIS 2015 - Proceedings

PB - Pacific Asia Conference on Information Systems

ER -