Automatic extraction of advice-revealing sentences for advice mining from online forums

Alfan Farizki Wicaksono, Sung Hyon Myaeng

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

11 Citations (Scopus)

Abstract

Web forums often contain explicit key learnings gleaned from people's experiences since they are platforms for personal communications on sharing information with others. One of the key learnings contained in Web forums is often expressed in the form of advice. As part of human experience mining from Web resources, we aim to provide a methodology to extract advice-revealing sentences from Web forums due to its usefulness, especially in travel domain. Instead of viewing the problem as a simple classification, we define it as a sequence labeling problem using various features. We identify three different types of features (i.e., syntactic features, context features, and sentence informativeness) and propose a new way of using Hidden Markov Model (HMM) for labeling sequential sentences, which in our experiment gave the best performance for our task. Moreover, the sentence informativeness score serves as an important feature for this task. It is worth noting that this work is the first attempt to extract advice-revealing sentences from Web forums.

Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Knowledge Capture
Subtitle of host publication"Knowledge Capture in the Age of Massive Web Data", K-CAP 2013
DOIs
Publication statusPublished - 2 Sep 2013
Event7th International Conference on Knowledge Capture: "Knowledge Capture in the Age of Massive Web Data", K-CAP 2013 - Banff, AB, Canada
Duration: 23 Jun 201326 Jun 2013

Publication series

NameProceedings of the 7th International Conference on Knowledge Capture: "Knowledge Capture in the Age of Massive Web Data", K-CAP 2013

Conference

Conference7th International Conference on Knowledge Capture: "Knowledge Capture in the Age of Massive Web Data", K-CAP 2013
CountryCanada
CityBanff, AB
Period23/06/1326/06/13

Keywords

  • Advice mining
  • Extension of HMM
  • Sequence labeling

Fingerprint Dive into the research topics of 'Automatic extraction of advice-revealing sentences for advice mining from online forums'. Together they form a unique fingerprint.

Cite this