Time-aware multi-viewpoint summarization of multilingual social text streams

Zhaochun Ren, Oana Inel, Lora Aroyo, Maarten De Rijke

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

A viewpoint is a triple consisting of an entity, a topic related to this entity and sentiment towards this topic. In time-aware multi-viewpoint summarization one monitors viewpoints for a running topic and selects a small set of informative documents. In this paper, we focus on time-aware multi-viewpoint summarization of multilingual social text streams. Viewpoint drift, ambiguous entities and multilingual text make this a challenging task. Our approach includes three core ingredients: dynamic viewpoint modeling, cross-language viewpoint alignment, and, finally, multi-viewpoint summarization. Specifically, we propose a dynamic latent factor model to explicitly characterize a set of viewpoints through which entities, topics and sentiment labels during a time interval are derived jointly; we connect viewpoints in different languages by using an entity-based semantic similarity measure; and we employ an update viewpoint summarization strategy to generate a time-aware summary to reflect viewpoints. Experiments conducted on a real-world dataset demonstrate the effectiveness of our proposed method for time-aware multi-viewpoint summarization of multilingual social text streams.

Original languageEnglish
Title of host publicationCIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery (ACM)
Pages387-396
Number of pages10
Volume24-28-October-2016
ISBN (Electronic)9781450340731
DOIs
Publication statusPublished - 24 Oct 2016
Event25th ACM International Conference on Information and Knowledge Management, CIKM 2016 - Indianapolis, United States
Duration: 24 Oct 201628 Oct 2016

Conference

Conference25th ACM International Conference on Information and Knowledge Management, CIKM 2016
CountryUnited States
CityIndianapolis
Period24/10/1628/10/16

Fingerprint

Summarization
Language
Sentiment
Latent factor models
Semantic similarity
Dynamic modeling
Experiment
Similarity measure
Alignment

Keywords

  • Dynamic viewpoint modeling
  • Multi-viewpoint summarization
  • Multilingual social text streams
  • Topic modeling

Cite this

Ren, Z., Inel, O., Aroyo, L., & De Rijke, M. (2016). Time-aware multi-viewpoint summarization of multilingual social text streams. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management (Vol. 24-28-October-2016, pp. 387-396). Association for Computing Machinery (ACM). https://doi.org/10.1145/2983323.2983710
Ren, Zhaochun ; Inel, Oana ; Aroyo, Lora ; De Rijke, Maarten. / Time-aware multi-viewpoint summarization of multilingual social text streams. CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Vol. 24-28-October-2016 Association for Computing Machinery (ACM), 2016. pp. 387-396
@inproceedings{754b5fa32cb3477c81b0b1477b77cc53,
title = "Time-aware multi-viewpoint summarization of multilingual social text streams",
abstract = "A viewpoint is a triple consisting of an entity, a topic related to this entity and sentiment towards this topic. In time-aware multi-viewpoint summarization one monitors viewpoints for a running topic and selects a small set of informative documents. In this paper, we focus on time-aware multi-viewpoint summarization of multilingual social text streams. Viewpoint drift, ambiguous entities and multilingual text make this a challenging task. Our approach includes three core ingredients: dynamic viewpoint modeling, cross-language viewpoint alignment, and, finally, multi-viewpoint summarization. Specifically, we propose a dynamic latent factor model to explicitly characterize a set of viewpoints through which entities, topics and sentiment labels during a time interval are derived jointly; we connect viewpoints in different languages by using an entity-based semantic similarity measure; and we employ an update viewpoint summarization strategy to generate a time-aware summary to reflect viewpoints. Experiments conducted on a real-world dataset demonstrate the effectiveness of our proposed method for time-aware multi-viewpoint summarization of multilingual social text streams.",
keywords = "Dynamic viewpoint modeling, Multi-viewpoint summarization, Multilingual social text streams, Topic modeling",
author = "Zhaochun Ren and Oana Inel and Lora Aroyo and {De Rijke}, Maarten",
year = "2016",
month = "10",
day = "24",
doi = "10.1145/2983323.2983710",
language = "English",
volume = "24-28-October-2016",
pages = "387--396",
booktitle = "CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management",
publisher = "Association for Computing Machinery (ACM)",

}

Ren, Z, Inel, O, Aroyo, L & De Rijke, M 2016, Time-aware multi-viewpoint summarization of multilingual social text streams. in CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. vol. 24-28-October-2016, Association for Computing Machinery (ACM), pp. 387-396, 25th ACM International Conference on Information and Knowledge Management, CIKM 2016, Indianapolis, United States, 24/10/16. https://doi.org/10.1145/2983323.2983710

Time-aware multi-viewpoint summarization of multilingual social text streams. / Ren, Zhaochun; Inel, Oana; Aroyo, Lora; De Rijke, Maarten.

CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Vol. 24-28-October-2016 Association for Computing Machinery (ACM), 2016. p. 387-396.

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Time-aware multi-viewpoint summarization of multilingual social text streams

AU - Ren, Zhaochun

AU - Inel, Oana

AU - Aroyo, Lora

AU - De Rijke, Maarten

PY - 2016/10/24

Y1 - 2016/10/24

N2 - A viewpoint is a triple consisting of an entity, a topic related to this entity and sentiment towards this topic. In time-aware multi-viewpoint summarization one monitors viewpoints for a running topic and selects a small set of informative documents. In this paper, we focus on time-aware multi-viewpoint summarization of multilingual social text streams. Viewpoint drift, ambiguous entities and multilingual text make this a challenging task. Our approach includes three core ingredients: dynamic viewpoint modeling, cross-language viewpoint alignment, and, finally, multi-viewpoint summarization. Specifically, we propose a dynamic latent factor model to explicitly characterize a set of viewpoints through which entities, topics and sentiment labels during a time interval are derived jointly; we connect viewpoints in different languages by using an entity-based semantic similarity measure; and we employ an update viewpoint summarization strategy to generate a time-aware summary to reflect viewpoints. Experiments conducted on a real-world dataset demonstrate the effectiveness of our proposed method for time-aware multi-viewpoint summarization of multilingual social text streams.

AB - A viewpoint is a triple consisting of an entity, a topic related to this entity and sentiment towards this topic. In time-aware multi-viewpoint summarization one monitors viewpoints for a running topic and selects a small set of informative documents. In this paper, we focus on time-aware multi-viewpoint summarization of multilingual social text streams. Viewpoint drift, ambiguous entities and multilingual text make this a challenging task. Our approach includes three core ingredients: dynamic viewpoint modeling, cross-language viewpoint alignment, and, finally, multi-viewpoint summarization. Specifically, we propose a dynamic latent factor model to explicitly characterize a set of viewpoints through which entities, topics and sentiment labels during a time interval are derived jointly; we connect viewpoints in different languages by using an entity-based semantic similarity measure; and we employ an update viewpoint summarization strategy to generate a time-aware summary to reflect viewpoints. Experiments conducted on a real-world dataset demonstrate the effectiveness of our proposed method for time-aware multi-viewpoint summarization of multilingual social text streams.

KW - Dynamic viewpoint modeling

KW - Multi-viewpoint summarization

KW - Multilingual social text streams

KW - Topic modeling

UR - http://www.scopus.com/inward/record.url?scp=84996524181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84996524181&partnerID=8YFLogxK

U2 - 10.1145/2983323.2983710

DO - 10.1145/2983323.2983710

M3 - Conference contribution

VL - 24-28-October-2016

SP - 387

EP - 396

BT - CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management

PB - Association for Computing Machinery (ACM)

ER -

Ren Z, Inel O, Aroyo L, De Rijke M. Time-aware multi-viewpoint summarization of multilingual social text streams. In CIKM 2016 - Proceedings of the 2016 ACM Conference on Information and Knowledge Management. Vol. 24-28-October-2016. Association for Computing Machinery (ACM). 2016. p. 387-396 https://doi.org/10.1145/2983323.2983710