Refine
Document Type
- Conference Proceeding (7)
- Part of a Book (1)
Language
- English (8)
Has Fulltext
- yes (8)
Is part of the Bibliography
- no (8)
Keywords
- Adjektiv (3)
- Opinion Mining (3)
- Adverb (2)
- Opinion Inference (2)
- Semantische Analyse (2)
- Sentiment Analysis (2)
- Adjective (1)
- Annotation (1)
- Automatische Sprachanalyse (1)
- Automatische Textanalyse (1)
Publicationstate
Reviewstate
- (Verlags)-Lektorat (3)
- Peer-Review (2)
In this contribution, we report on an effort to annotate German data with information relevant to opinion inference. Such information has previously been referred to as effect or couched in terms of eventevaluation functors. We extend the theory and present an extensive scheme that combines both approaches and thus extends the set of inference-relevant predicates. Using these guidelines to annotate 726 German synsets, we achieve good inter-annotator agreement.
Scales and Scores. An evaluation of methods to determine the intensity of subjective expressions
(2015)
In this contribution, we present a survey of several methods that have been applied to the ordering of various types of subjective expressions (e.g. good < great), in particular adjectives and adverbs. Some of these methods use linguistic regularities that can be observed in large text corpora while others rely on external grounding in metadata, in particular the star ratings associated with product reviews. We discuss why these methods do not work uniformly across all types of expressions. We also present the first application of some of these methods to the intensity ordering of nouns (e.g. moron < dummy).
In recent years, theoretical and computational linguistics has paid much attention to linguistic items that form scales. In NLP, much research has focused on ordering adjectives by intensity (tiny < small). Here, we address the task of automatically ordering English adverbs by their intensifying or diminishing effect on adjectives (e.g. extremely small < very small). We experiment with 4 different methods: 1) using the association strength between adverbs and adjectives; 2) exploiting scalar patterns (such as not only X but Y); 3) using the metadata of product reviews; 4) clustering. The method that performs best is based on the use of metadata and ranks adverbs by their scaling factor relative to unmodified adjectives.
There is increasing interest in recognizing opinion inferences in addition to expressions of explicit sentiment. While different formalisms for representing inferential mechanisms are being developed and lexical resources are being built alongside, we here address the need for deeper investigation of the robustness of various aspects of opinion inference, performing crowdsourcing experiments with constructed stimuli as well as a corpus study of attested data.
Sentiment analysis has so far focused on the detection of explicit opinions. However, of late implicit opinions have received broader attention, the key idea being that the evaluation of an event type by a speaker depends on how the participants in the event are valued and how the event itself affects the participants. We present an annotation scheme for adding relevant information, couched in terms of so-called effect functors, to German lexical items. Our scheme synthesizes and extends previous proposals. We report on an inter-annotator agreement study. We also present results of a crowdsourcing experiment to test the utility of some known and some new functors for opinion inference where, unlike in previous work, subjects are asked to reason from event evaluation to participant evaluation.
In this paper, we report on an effort to develop a gold standard for the intensity ordering of subjective adjectives. Rather than pursue a complete order as produced by paying attention to the mean scores of human ratings only, we take into account to what extent assessors consistently rate pairs of adjectives relative to each other. We show that different available automatic methods for producing polar intensity scores produce results that correlate well with our gold standard, and discuss some conceptual questions surrounding the notion of polar intensity.
We compare several different corpus- based and lexicon-based methods for the scalar ordering of adjectives. Among them, we examine for the first time a low- resource approach based on distinctive- collexeme analysis that just requires a small predefined set of adverbial modifiers. While previous work on adjective intensity mostly assumes one single scale for all adjectives, we group adjectives into different scales which is more faithful to human perception. We also apply the methods to both polar and non-polar adjectives, showing that not all methods are equally suitable for both types of adjectives.