Extracting Opinions, Opinion Holders, and Topics Expressed in Online News Media Text

By Soo-Min Kim, Eduard H. Hovy. 2006

526 citations recorded by the source corpus.

This paper presents a method for identifying an opinion with its holder and topic, given a sentence from online news media texts. We introduce an approach of exploiting the semantic structure of a sentence, anchored to an opinion bearing verb or adjective. This method uses semantic role labeling as an intermediate step to label an opinion holder and topic using data from FrameNet. We decompose our task into three phases: identifying an opinion-bearing word, labeling semantic roles related to the word in the sentence, and then finding the holder and the topic of the opinion word among the labeled semantic roles. For a broader coverage, we also employ a clustering technique to predict the most probable frame for a word which is not defined in FrameNet. Our experimental results show that our system performs significantly better than the baseline.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/42e4765f00de618dc03a4be3dd6f6f41b4bbbeae

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research (2020, methodology): “These works include approaches that use named-entity recognition, Kim & Hovy [94], parsing and ranking candidates, Kim&Hovy [95], semantic role labeling, Wiegand & Ruppenhofer [224], structured prediction using CRFs, Choi et al.”
A survey of sentiment analysis in social media (2018, background): “Several researches have investigated on opinion holder extraction based on conditional random ﬁelds (CRF) [26], maximum entropy (ME) model [57], convolution kernels [140], and dependency parser method [68], or automatic semantic role labeling (ASRL) [108].”
Argument Mining: A Survey (2020, background): “In Kim and Hovy (2006a), the link between argument mining and opinion mining is clearer still.”
Affective News: The Automated Coding of Sentiment in Political Texts (2012, background): “For examples in computational linguistics, see, for instance, Généreux and Evans (2006); Hatzivassiloglou and McKeown (1997); Joachims (1998); Kim and Hovy (2006); Kushal, Lawrence, and Pennock (2003); Leshed and Kaye (2006); Mishne (2005); Pang et al. (2002); and Wiebe (2000).”
Semantic Frames to Predict Stock Price Movement (2013, methodology): “Semantic role labeling using FrameNet has been used to identify an opinion with its holder and topic (Kim and Hovy, 2006).”
Multi-entity Sentiment Scoring (2009, methodology): “[ 7] extract HOLDER s and TOPIC s using opinion verbs and adjectives, and FrameNet-driven semantic frame role labelling.”
Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields (2010, background): “Kim and Hovy (2006) aim at extracting opinion holders and opinion targets in newswire with semantic role labeling.”
Grammatical structures for word-level sentiment detection (2012, background): “Existing work in this area often uses semantic frames and role labeling (Kim and Hovy, 2006; Choi et al., 2006), but resources typically used in these tasks (e.g. FrameNet) are not exhaustive.”
Towards detecting influenza epidemics by analyzing Twitter messages (2010, background): “Most other related work in analyzing user-generated Web content is motivated by marketing applications, in which a client determines the impact of a marketing strategy by mining changes in consumer reception of the product from blog posts, product reviews, or Twitter messages [11, 14, 13].”
Using Sequence Kernels to identify Opinion Entities in Urdu (2011, background): “Kim and Hovy (2006) map the semantic frames of FrameNet (Baker et al., 1998) into opinion holder and target for adjectives and verbs to identify these components.”