Using a new multimodal dataset consisting of sentiment annotated utterances extracted from video reviews, we show that multimodal sentiment analysis can be effectively performed, and that the joint use of visual, acoustic, and linguistic modalities can lead to error rate reductions of up to 10.5% as compared to the best performing individual modality.

Video-level sentiment analysis .

Second, previous work in subjectivity and sentiment analysis has demonstrated that a layered approach (where neutral statements are first separated from opinion statements followed by a separation between positive and negative statements) works better than a single three-way classification.

This is in line with earlier work on text-based sentiment analysis , where it has been observed that full-document reviews often contain both positive and negative comments, which led to a number of methods addressing opinion analysis at sentence level.

In our work, this dataset enabled a wide range of multimodal sentiment analysis experiments, addressing the relative importance of modalities and individual features.

The following section presents related work in text-based sentiment analysis and audiovisual emotion recognition.

In this section we provide a brief overview of related work in text-based sentiment analysis , as well as audiovisual emotion analysis.

2.1 Text-based Subjectivity and Sentiment Analysis

The techniques developed so far for subjectivity and sentiment analysis have focused primarily on the processing of text, and consist of either rule-based classifiers that make use of opinion lexicons, or data-driven methods that assume the availability of a large dataset annotated for polarity.

In this paper, the problem of data sparsity in sentiment analysis , both monolingual and cross-lingual, is addressed through the means of clustering.

Experiments show that cluster based data sparsity reduction leads to performance better than sense based classification for sentiment analysis at document level.

Similar idea is applied to Cross Lingual Sentiment Analysis (CLSA), and it is shown that reduction in data sparsity (after translation or bilingual-mapping) produces accuracy higher than Machine Translation based CLSA and sense based CLSA.

Given that sentiment analysis is a less resource intensive task compared to machine translation, the use of an MT system is hard to justify for performing

The reason for the drop in the accuracy of approach based on sense features for En-PD dataset is the domain specific nature of sentiment analysis (Blitzer et al., 2007), which is explained in the next point.

One such application is Sentiment Analysis (SA) (Pang and Lee, 2002).

In the current work, this particular insight is used to solve the data sparsity problem in the sentiment analysis by leveraging unlabelled monolingual corpora.

Popular approaches for Cross-Lingual Sentiment Analysis (CLSA) (Wan, 2009; Duh et al., 2011) depend on Machine Translation (MT) for converting the labeled data from one language to the other (Hiroshi et al., 2004; Banea et al., 2008; Wan, 2009).

There has been research related to clustering and sentiment analysis .

(2011) attempts to cluster features of a product to perform sentiment analysis on product reviews.

In situations where labeled data is not present in a language, approaches based on cross-lingual sentiment analysis are used.

We propose a new concept, sentiment relevance, to make this distinction and argue that it better reflects the requirements of sentiment analysis systems.

We introduced sentiment relevance to make this distinction and argued that it better reflects the requirements of sentiment analysis systems.

It is generally recognized in sentiment analysis that only a subset of the content of a document contributes to the sentiment it conveys.

Some sentiment analysis systems filter out objective language and predict sentiment based on subjective language only because objective statements do not directly reveal sentiment.

they are not optimal for sentiment analysis .

Many publications have addressed subjectivity in sentiment analysis .

As we argue above, if the goal is to identify parts of a document that are useful/non-useful for sentiment analysis , then S-relevance is a better notion to use.

Transfer learning has been applied previously in sentiment analysis (Tan and Cheng, 2009), targeting polarity detection.

Sentiment analysis (Pang and Lee, 2008) has been successfully applied to mine social media data for emotional responses to events, public figures, and consumer products just by using emotion lexicons—lists that map words to polarity values (+1 for positive sentiment, -l for negative) or valence values that try to capture degrees of polarity.

plays.1 2 Sentiment Analysis and Related Work

Sentiment analysis (SA) is now widely used commercially to infer user opinions from product reviews and social-media messages (Pang and Lee,

Thwarting and sarcasm are two uncharted territories in sentiment analysis , the former because of the lack of training corpora and the latter because of the enormous amount of world knowledge it demands.

This definition emphasizes thwarting as piggy-backing on sentiment analysis to improve the latter’s performance.

Although much research has been done in the field of sentiment analysis (Liu et al., 2012), thwarting and sarcasm are not addressed, to the best of our knowledge.

Thwarting has been identified as a common phenomenon in sentiment analysis (Pang et al., 2002, Ohana et al., 2009, Brooke, 2009) in various forms of texts but no previous work has proposed a solution to the problem of identifying thwarting.

The basic objective for creating a thwarting detection system was to include such a module in the general sentiment analysis framework.

Thus, using document polarity as a feature contradicts the objective of sentiment analysis , which is to find the document polarity.

p@n is commonly used to evaluate a ranking when the total number of correct items is unknown (e.g., Web search results, aspect terms in topic models for sentiment analysis (Zhao et al., 2010), etc.).

AD-expressions are crucial for the analysis of interactive discussions and debates just as sentiment expressions are instrumental in sentiment analysis (Liu, 2012).

Sentiment analysis: Sentiment analysis determines positive and negative opinions expressed on entities and aspects (Hu and Liu, 2004).

Thus, this work expands the sentiment analysis research.

Also related are topic models in sentiment analysis which are often referred to as Aspect and Sentiment models (ASMs).

In contrast, most of the previous work on sentiment analysis in social media does not consider these kinds of problems (Barbosa and Feng, 2010; Davidov et al., 2010; Speriosu et al., 2011).

We used the sentiment analyzer created by Kanayama and Na-sukawa (2012) to detect a phrase representing neg-

The sentiment analyzer can find not only sentiment phrases but the targets of the phrases based on syntactic parsing and the case framesl.

This suggests that full-fledged sentiment analysis is not effective at least in this setting.

An evident alternative to this approach is to use sentiment analysis (Mandel et al., 2012; Tsagkali-dou et al., 2011) assuming that problem reports should include something ‘bad’ while aid messages describe something ‘good’.

Word Sentiment Polarity (WSP) As we suggested before, full-fledged sentiment analysis to recognize the expressions, including clauses and phrases, that refer to something good or bad was not effective in our task.

To identify the sentiment polarity of words, we employed the word sentiment polarity dictionary used with a sentiment analysis tool for Japanese, the Opinion Extraction Tool software2, which is an implementation of Nakagawa et al.

Note that we used the Opinion Extraction Tool in the experiments to check the effectiveness of the full-fledged sentiment analysis in this task.

Previously, RAE have successfully been applied to a number of tasks including sentiment analysis , paraphrase detection, relation extraction

The first task of sentiment analysis allows us to compare our CCG-conditioned RAE with similar, existing models.

5.1 Sentiment Analysis

The effect of this was highlighted by the sentiment analysis task, with the more complex models performing

They also tend to incorporate handcrafted lists of search terms to filter irrelevant content and use sentiment analysis lexicons for extracting opinion bias.

In this paper, we propose a generic method that aims to be independent of the characteristics described above (use of search terms or sentiment analysis tools).

majority of sentiment analysis tools are English-specific (or even American English) and, most importantly, political word lists (or ontologies) change in time, per country and per party; hence, generalisable methods should make an effort to limit reliance from such tools.

In experiments with text topic classification and sentiment analysis , we show that our method is both more scalable and more accurate than SSL techniques from previous work.

Our experiments demonstrate that MNB-FM outperforms previous approaches across multiple text classification techniques including topic classification and sentiment analysis .

In experiments across topic classification and sentiment analysis , MNB-FM was found to be more accurate and more scalable than several supervised and semi-supervised baselines from previous work.

(2011) introduced a hybrid approach for stock sentiment analysis based on companies’ news articles.

LDA can learn a predefined number of topics and has been widely applied in its extended forms in sentiment analysis and many other tasks (Mei et al., 2007; Branavan et al., 2008; Lin and He, 2009; Zhao et al., 2010; Wang et al., 2010; Brody and Elhadad, 2010; Jo and Oh, 2011; Moghaddam and Ester, 2011; Sauper et al., 2011; Mukherjee and Liu, 2012; He et al., 2012).

In this work, we employ topic based sentiment analysis using DPM on Twitter posts (or tweets).

(2009) introduced part-of-speech specific DAL features for sentiment analysis .

Sentiment analysis figures strongly in NLP work on news.

For deep representation of sentiment analysis , Ruppenhofer and Rehbein (2012) propose SentiFrameNet.