Citation Context

...the spectrum from terrible and awful. Thus, we extend the model with a supervised sentiment component that is capable of embracing many social and attitudinal aspects of meaning (Wilson et al., 2004; =-=Alm et al., 2005-=-; Andreevskaia and Bergler, 2006; Pang and Lee, 2005; Goldberg and Zhu, 2006; Snyder and Barzilay, 2007). This 1 Introduction component of the model uses the vector represenWord representations are a ...

Citation Context

... whose emotions are known (Read, 2004), some use hand-coded rules (Neviarouskaya et al., 2009, 2010), and some use machine learning and a number of emotion features, including emotion denoting words (=-=Alm et al., 2005-=-; Aman and Szpakowicz, 2007). Recent work by Bellegarda (2010) uses sophisticated dimension reduction techniques (variations of latent semantic analysis), to automatically identify emotion terms, and ...

Citation Context

...eeling, and pain but these have not been exploited to a significant degree by the natural language processing 2http://wndomains.fbk.eu/wnaffect.html 3http://www.wjh.harvard.edu/∼inquirer community. Work in emotion detection can be roughly classified into that which looks for specific emotion denoting words (Elliott, 1992), that which determines tendency of terms to co-occur with seed words whose emotions are known (Read, 2004), that which uses hand-coded rules (Neviarouskaya et al., 2009), and that which uses machine learning and a number of emotion features, including emotion denoting words (Alm et al., 2005). Much of this recent work focuses on six emotions studied by Ekman (1992). These emotions— joy, sadness, anger, fear, disgust, and surprise— are a subset of the eight proposed in Plutchik (1980). We focus on the Plutchik emotions because the emotions can be naturally paired into opposites—joy– sadness, anger–fear, trust–disgust, and anticipation– surprise. Natural symmetry apart, we believe that prior work on automatically computing word–pair antonymy (Lin et al., 2003; Mohammad et al., 2008; Lobanova et al., 2010) can now be leveraged in automatic emotion detection. 3 Emotion annotation In t...

Citation Context

... researchers have studied emotion in a wider framework of private states [12]. Wiebe et al. [20] worked on the manual annotation of private states including emotions, opinions, and sentiment in a 10,000-sentence corpus (the MPQA corpus) of news articles. Expressions of emotions in text have also been studied within the Appraisal Framework [5], a functional theory of the language used for conveying attitudes, judgments and emotions [15, 19]. Neither of these frameworks deals exclusively with emotion, the focus of this paper. In a work focused on learning specific emotions from text, Alm et al. [1] have explored automatic classification of sentences in children's fairy tales according to the basic emotions identified by Ekman [3]. The data used in their experiments was manually annotated with emotion information, and is targeted for use in a text-tospeech synthesis system for expressive rendering of stories. Read [14] has used a corpus of short stories, manually annotated with sentiment tags, in automatic emotion-based classification of sentences. These projects focus on the genre of fiction, with only sentence-level emotion annotations; they do not identify emotion indicators within a ...

Citation Context

...ining opinions from product reviews (e.g., (Morinaga et al., 2002; Nasukawa and Yi, 2003; Yi et al., 2003; Hu and Liu, 2004; Popescu and Etzioni, 2005)), automatic expressive text-tospeech synthesis (=-=Alm, Roth, and Sproat, 2005-=-), information extraction (e.g., (Riloff, Wiebe, and Phillips, 2005)), and question answering (e.g., (Yu and Hatzivassiloglou, 2003; Stoyanov, Cardie, and Wiebe, 2005)). There are a number of other to...

Citation Context

...ng the two modalities. 2. Related Work Although there is some existing work dealing with audio mood classification (e.g. [11, 9, 18, 21]), and also some recent literature about mood detection in text =-=[2, 13]-=-, very little has been done so far to address the automatic classification of lyrics according to their mood. We have found no prior articles studying the combination of lyrics and acoustic informatio...

Citation Context

...ntiment analysis focuses on the automatic identification of private states, such as opinions, emotions, sentiments, evaluations, beliefs, and speculations in natural language. While subjectivity classification labels text as either subjective or objective, sentiment or polarity classification adds an additional level of granularity, by further classifying subjective text as either positive, negative or neutral. To date, a large number of text processing applications have used techniques for automatic sentiment and subjectivity analysis, including automatic expressive text-to-speech synthesis (Alm et al., 1990), tracking sentiment timelines in on-line forums and news (Balog et al., 2006; Lloyd et al., 2005), and mining opinions from product reviews (Hu and Liu, 2004). In many natural language processing tasks, subjectivity and sentiment classification has been used as a first phase filtering to generate more viable data. Research that benefited from this additional layering ranges from question answering (Yu and Hatzivassiloglou, 2003), to conversation summarization (Carenini et al., 2008), and text semantic analysis (Wiebe and Mihalcea, 2006; Esuli and Sebastiani, 2006a). Although subjectivity tend...

Citation Context

... stock message boards (Das and Chen, 2001), distinguishing editorials from news articles (Wiebe, Wilson, and Bell, 2001; Yu and Hatzivassiloglou, 2003), automatic expressive text-to-speech synthesis (=-=Alm, Roth, and Sproat, 2005-=-), information extraction (Riloff, Wiebe, and Phillips, 2005), question answering (Yu and Hatzivassiloglou, 2003; Stoyanov, Cardie, and Wiebe, 2005), multi-document summarization (Seki et al., 2005), ...