The analysis of emotion, affect and sentiment from visual content has become an exciting area in the multimedia community allowing to build new applications for brand monitoring, advertising, and opinion mining. There exists no corpora for sentiment analysis on visual content, and therefore limits the progress in this critical area. To stimulate innovative research on this challenging issue, we constructed a new benchmark and database (you can browse the database at VSO Browsing Interface). This database contains a Visual Sentiment Ontology (VSO) consisting of 3244 adjective noun pairs (ANP), SentiBank a set of 1200 trained visual concept detectors providing a mid-level representation of sentiment, associated training images acquired from Flickr, and a benchmark containing 603 photo tweets covering a diverse set of 21 topics.

This website provides the above mentioned material for download and is structured as the following:
Benchmark and Dataset Citation
Damian Borth, Rongrong Ji, Tao Chen, Thomas Breuel and Shih-Fu Chang. "Large-scale Visual Sentiment Ontology and Detectors Using Adjective Noun Pairs," ACM Multimedia Conference, Barcelona, Oct 2013.
download paper    
download material
Update: Thanks for checking out VSO, you may also be interested in our new expanded and multilingual version MVSO

Visual Sentiment Ontology: Ontology and Concepts Visual Sentiment Ontology: Image Dataset SentiBank: Visual Sentiment Concept Classifiers Photo Tweet
Sentiment Benchmark
The benchmark includes 603 tweets with photos and is intended for evaluating the performance of automatic sentiment prediction using features of different modalities (text only, image only, and text-image combined). It was collected in November 2012 via the PeopleBrowsr API using 21 hashtags listed below. Ground truths of sentiment values were obtained by Amazon Mechanic Turk annotation, resulting in 470 positive and 133 negative labels.

    #abortion, #religion, #cancer, #aids,
    #police, #globalwarming, #gaymarriage
    #election, #hurricanesandy, #blackfriday,
    #agt (america got talent), #nfl,
    #championsleague, #decemberwish,
    #cairo, #newyork
    #android, #applefanboy
    #obama, #zimmerman

Ground truth labeling
To obtain sentiment ground truth for the collected image tweets, Amazon Mechanical Turk annotation was used. Three labeling runs, namely image only inspection, text only inspection, and full inspection of both image and text contained in the tweet, have been performed on 2000 image tweets of different hashtags. For each run and each tweet, 3 independent Turkers were asked to label the sentiment label (positive, negative, or neutral). The figure on the upper right shows the percentage of tweeets that receive three completely different labels, confirming the benefits of inspecting both image and text content. At the end, only tweets with unanimous labels (agreed by all three Turkers) are included in the released benchmark (603 tweets).

Sentiment Prediction Performance
Fig. 2 and Fig. 3 shows the accuracy of predicting the sentiment values of photo tweets using late fusion of text-based classifiers and visual concept based classifiers (SentiBank v1.02 and SentiBank v1.1 respectively). For details please see the paper
*The Phototweet sentiment prediction experiment in the paper used SentiBank v1.01.

Files for Download
1. Phototweet Sentiment Benchmark:
   - tweet text
   - tweet photo
   - sentiment label (pos., neg.).
2. Dataset partitions for training and
   testing the baseline prediction system
   (5 runs, see details in paper)

Fig.1 The volumes and label disagreements for different hashtags. For each hashtag, the total number of images is shown, in addition to the number of images receiving complete disagreement among turkers (i.e., 3 different sentiment labels: positive, negative and neural), while labeling is done using text only, image only, and joint image-text combined.
Sentiment Prediction Performance
We implemented a baseline system for sentiment prediction of image tweets. The systems employs SentiBank visual concept features in combination with text-based sentiment classification in a late-fusion setup. The following figure shows the prediction accuracy for tweets of each hashtag."

Fig.2 Phototweet sentiment prediction accuracy over different hashtags by using text only (SentiStrength), visual only (SentiBank v1.02), and combination. Accuracy averaged over 5 runs. Fig.2 Phototweet sentiment prediction accuracy over different hashtags by using text only (SentiStrength), visual only (SentiBank v1.1), and combination. Accuracy averaged over 5 runs. The overall accuracy increased from 72% (v1.02) to 76% (v1.1).

By downloading the Photo Tweet dataset, you agree that 1) the use of the data is restricted to research or education purpose only, 2) all copyright and license restrictions associated with the dataset/code will be followed, and 3) the authors of the above paper and their affiliated organizations make no warranties regarding the database or software, including but not limited to non-infringement.