Multimodal Sentiment Analysis of Spanish Online Videos

  title={Multimodal Sentiment Analysis of Spanish Online Videos},
  author={Ver{\'o}nica P{\'e}rez-Rosas and Rada Mihalcea and Louis-Philippe Morency},
  journal={IEEE Intelligent Systems},
Using multimodal sentiment analysis, the presented method integrates linguistic, audio, and visual features to identify sentiment in online videos. In particular, experiments focus on a new dataset consisting of Spanish videos collected from YouTube that are annotated for sentiment polarity. 

Figures and Tables from this paper

Multimodal Sentiment Analysis
This chapter discusses the major research challenges in this topic followed by the overview of the proposed multimodal sentiment analysis framework.
Combining Textual Clues with Audio-Visual Information for Multimodal Sentiment Analysis
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.
Speaker-Independent Multimodal Sentiment Analysis for Big Data
This chapter proposes a contextual multimodal sentiment analysis framework which outperforms the state of the art and addresses the generalizability issue of the proposed method.
Survey on Sentiment Analysis from Affective Multimodal Content
This paper presents the overview of different techniques and approaches in sentiment analysis for text, audio, and visual modalities for text and emotion recognition from audio and visual.
MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos
This paper introduces to the scientific community the first opinion-level annotated corpus of sentiment and subjectivity analysis in online videos called Multimodal Opinion-level Sentiment Intensity dataset (MOSI), which is rigorously annotated with labels for subjectivity, sentiment intensity, per-frame and per-opinion annotated visual features, andper-milliseconds annotated audio features.
A Sneak Preview of Sentiment Analysis
  • Roopal Mamtora, L. Ragha
  • Computer Science
    2018 International Conference on Smart City and Emerging Technology (ICSCET)
  • 2018
This survey paper contributes towards complete information about emotions detected in various modalities, tasks, techniques, application domains and available built-in resources related to sentiment analysis.
A Novel Context-Aware Multimodal Framework for Persian Sentiment Analysis
Multimodal sentimental analysis for social media applications: A comprehensive review
This work aims to present a survey of recent developments in analyzing the multimodal sentiments (involving text, audio, and video/image) which involve human–machine interaction and challenges involved in analyzing them.
Multimodal sentiment analysis: Sentiment analysis using audiovisual format
Audiovisual input is taken and emotions from video and audio in parallel from audiovisually input are extracted and the overall review is classified as positive, negative or neutral based on the emotions detected.
Utterance-Level Multimodal Sentiment Analysis
It is shown 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.


Towards multimodal sentiment analysis: harvesting opinions from the web
This paper addresses the task of multimodal sentiment analysis, and conducts proof-of-concept experiments that demonstrate that a joint model that integrates visual, audio, and textual features can be effectively used to identify sentiment in Web videos.
Annotating Expressions of Opinions and Emotions in Language
The manual annotation process and the results of an inter-annotator agreement study on a 10,000-sentence corpus of articles drawn from the world press are presented.
SemEval-2007 Task 14: Affective Text
The data set used in the evaluation and the results obtained by the participating systems are described, meant as an exploration of the connection between emotions and lexical semantics.
A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts
A novel machine-learning method is proposed that applies text-categorization techniques to just the subjective portions of the document, which greatly facilitates incorporation of cross-sentence contextual constraints.
Large-Scale Sentiment Analysis for News and Blogs (system demonstration)
A system that assigns scores indicating positive or negative opinion to each distinct entity in the text corpus, consisting of a sentiment identication phase, and a sentiment aggregation and scoring phase, which scores each entity relative to others in the same class.
Learning Word Vectors for Sentiment Analysis
This work presents a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term--document information as well as rich sentiment content, and finds it out-performs several previously introduced methods for sentiment classification.
Why Are They Excited? Identifying and Explaining Spikes in Blog Mood Levels
Simple techniques based on comparing corpus frequencies, coupled with large quantities of data, are shown to be effective for identifying the events underlying changes in global moods.
Target-dependent Twitter Sentiment Classification
This paper proposes to improve target-dependent Twitter sentiment classification by incorporating target- dependent features; and taking related tweets into consideration; and according to the experimental results, this approach greatly improves the performance of target- dependence sentiment classification.
Co-Training for Cross-Lingual Sentiment Classification
A cotraining approach is proposed to making use of unlabeled Chinese data for cross-lingual sentiment classification, which leverages an available English corpus for Chinese sentiment classification by using the English corpus as training data.
Multimodal Subjectivity Analysis of Multiparty Conversation
The experiments show that character-level features outperform wordlevel features for these tasks, and that a careful fusion of all features yields the best performance.