Newton Howard

Enhanced SenticNet with Affective Labels for Concept-Based Opinion Mining

SenticNet 1.0 is one of the most widely used, publicly available resources for concept-based opinion mining. The presented methodology enriches SenticNet concepts with affective information by assigning an emotion label.

Fusing audio, visual and textual clues for sentiment analysis from multimodal content

A huge number of videos are posted every day on social media platforms such as Facebook and YouTube. This makes the Internet an unlimited source of information. In the coming decades, coping with such information and mining useful knowledge from it will be an increasingly difficult task. In this paper, we propose a novel methodology for multimodal sentiment analysis, which consists in harvesting sentiments from Web videos by demonstrating a model that uses audio, visual and textual modalities as sources of information. We used both feature- and decision-level fusion methods to merge affective information extracted from multiple modalities. A thorough comparison with existing works in this area is carried out throughout the paper, which demonstrates the novelty of our approach. Preliminary comparative experiments with the YouTube dataset show that the proposed multimodal system achieves an accuracy of nearly 80%, outperforming all state-of-the-art systems by more than 20%.

Semantic Multidimensional Scaling for Open-Domain Sentiment Analysis

The ability to understand natural language text is far from being emulated in machines. One of the main hurdles to overcome is that computers lack both the common and common-sense knowledge that humans normally acquire during the formative years of their lives. To really understand natural language, a machine should be able to comprehend this type of knowledge, rather than merely relying on the valence of keywords and word co-occurrence frequencies. In this article, the largest existing taxonomy of common knowledge is blended with a natural-language-based semantic network of common-sense knowledge. Multidimensional scaling is applied on the resulting knowledge base for open-domain opinion mining and sentiment analysis.

Common Sense Knowledge Based Personality Recognition from Text

Past works on personality detection has shown that psycho-linguistic features, frequency based analysis at lexical level, emotive words and other lexical clues such as number of first person or second person words carry major role to identify personality associated with the text. In this work, we propose a new architecture for the same task using common sense knowledge with associated sentiment polarity and affective labels. To extract the common sense knowledge with sentiment polarity scores and affective labels we used Senticnet which is one of the most useful resources for opinion mining and sentiment analysis. In particular, we combined common sense knowledge based features with phycho-linguistic features and frequency based features and later the features were employed in supervised classifiers. We designed five SMO based supervised classifiers for five personality traits. We observe that the use of common sense knowledge with affective and sentiment information enhances the accuracy of the existing frameworks which use only psycho-linguistic features and frequency based analysis at lexical level.

Dependency-Based Semantic Parsing for Concept-Level Text Analysis

Concept-level text analysis is superior to word-level analysis as it preserves the semantics associated with multi-word expressions. It offers a better understanding of text and helps to significantly increase the accuracy of many text mining tasks. Concept extraction from text is a key step in concept-level text analysis. In this paper, we propose a ConceptNet-based semantic parser that deconstructs natural language text into concepts based on the dependency relation between clauses. Our approach is domain-independent and is able to extract concepts from heterogeneous text. Through this parsing technique, 92.21% accuracy was obtained on a dataset of 3,204 concepts. We also show experimental results on three different text analysis tasks, on which the proposed framework outperformed state-of-the-art parsing techniques.

Metaphor Identification in Large Texts Corpora

Identifying metaphorical language-use (e.g., sweet child) is one of the challenges facing natural language processing. This paper describes three novel algorithms for automatic metaphor identification. The algorithms are variations of the same core algorithm. We evaluate the algorithms on two corpora of Reuters and the New York Times articles. The paper presents the most comprehensive study of metaphor identification in terms of scope of metaphorical phrases and annotated corpora size. Algorithms’ performance in identifying linguistic phrases as metaphorical or literal has been compared to human judgment. Overall, the algorithms outperform the state-of-the-art algorithm with 71% precision and 27% averaged improvement in prediction over the base-rate of metaphors in the corpus.

Ensemble application of convolutional neural networks and multiple kernel learning for multimodal sentiment analysis

Abstract The advent of the Social Web has enabled anyone with an Internet connection to easily create and share their ideas, opinions and content with millions of other people around the world. In pace with a global deluge of videos from billions of computers, smartphones, tablets, university projectors and security cameras, the amount of multimodal content on the Web has been growing exponentially, and with that comes the need for decoding such information into useful knowledge. In this paper, a multimodal affective data analysis framework is proposed to extract user opinion and emotions from video content. In particular, multiple kernel learning is used to combine visual, audio and textual modalities. The proposed framework outperforms the state-of-the-art model in multimodal sentiment analysis research with a margin of 10–13% and 3–5% accuracy on polarity detection and emotion recognition, respectively. The paper also proposes an extensive study on decision-level fusion.

Music Genre Classification: A Semi-supervised Approach

Music genres can be seen as categorical descriptions used to classify music basing on various characteristics such as instrumentation, pitch, rhythmic structure, and harmonic contents. Automatic music genre classification is important for music retrieval in large music collections on the web. We build a classifier that learns from very few labeled examples plus a large quantity of unlabeled data, and show that our methodology outperforms existing supervised and unsupervised approaches. We also identify salient features useful for music genre classification. We achieve 97.1% accuracy of 10-way classification on real-world audio collections.

Computational Intelligence for Big Social Data Analysis [Guest Editorial]

The articles in this special section focus on computational intelligence for big social data analytics. In the eras of social connectedness and social colonization, people are becoming increasingly enthusiastic about interacting, sharing, and collaborating through online collaborative media. In recent years, this collective intelligence has spread to many different areas, with particular focus on fields related to everyday life such as commerce, tourism, education, and health, causing the size of the Social Web to expand exponentially. The distillation of knowledge from such a large amount of unstructured information, however, is an extremely difficult task, as the contents of todays Web are perfectly suitable for human consumption, but remain hardly understandable to machines. Big social data analysis grows out of this need and combines multiple disciplines such as social network analysis, multimedia management, social media analytics, trend discovery, and opinion mining.

Sentic blending: Scalable multimodal fusion for the continuous interpretation of semantics and sentics

The capability of interpreting the conceptual and affective information associated with natural language through different modalities is a key issue for the enhancement of human-agent interaction. The proposed methodology, termed sentic blending, enables the continuous interpretation of semantics and sentics (i.e., the conceptual and affective information associated with natural language) based on the integration of an affective common-sense knowledge base with any multimodal signal-processing module. In this work, in particular, sentic blending is interfaced with a facial emotional classifier and an opinion mining engine. One of the main distinguishing features of the proposed technique is that it does not simply perform cognitive and affective classification in terms of discrete labels, but it operates in a multidimensional space that enables the generation of a continuous stream characterising users semantic and sentic progress over time, despite the outputs of the unimodal categorical modules have very different time-scales and output labels.