**2. Related Work**

Sentiment analysis is extensively studied since the early 2000s [**? ?** ]. With the advent of internet, OSNs soon became the most used source for sentiment analysis [**? ?** ]. Some of the applications of sentiment analysis are: marketing [**?** ], politics [**?** ], and more recently medicine [**? ?** ]. Affective computing, as suggested by Picard [**?** ], has sparked the interest in the specific emotion analysis of texts [**? ?** ].

Machine learning has been successfully applied to sentiment analysis of texts [**???** ]. ML methods that have been used for sentiment analysis are: Support Vector Machines [**? ?** ], Multinomial Naïve Bayes [**?** ] and Decision Trees [**?** ], while DNNs were introduced more recently [**? ?** ].

DNNs can be used in text related applications as well. In [**?** ] Severyn and Moschitti rerank short texts in pairs and present the per pair relation without manual feature engineering. Lai et al. [**?** ] perform unsupervised text classification and highlight key text components in the process via a recurrent convolutional neural network. The authors of [**?** ] perform a named entity recognition task and generate relevant word embedding with two separate DNNs. Text generation is addressed via a recurrent neural network in [**?** ] and an extensively trained model outperforms the best non-NN models. Sentiment classification of textual sources had its own fair share of DNN implementations [**???** ].

Learning ensembles have been used to combine different types of information, such as audio video and text towards sentiment and emotional classification [**?** ]. Araque et al. use an ensemble of classifiers that combines features and word vectors [**?** ] for sentiment classification with greater than 80% F-Score. A soft voting ensemble is used in [**?** ] for topic-document and document classification the results suggesting a significant improvement over single-model methods. The authors of [**?** ] use a stacked two-layer ensemble of CNN to predict the message level sentiment of Tweets, with the addition of a distant supervision phase. A pseudo-ensemble, essentially an ensemble of similar models trained on noisy sub-data, is used for sentiment analysis purposes in [**?** ], but is ineffective for regression classification problems.

Multilabel classification problems assign multiple classes per item. Such problems are frequently observed in the field of computer vision [**???** ]. With regards to multilabel text-based sentiment analysis, Chen et al. [**?** ] propose an ensemble of a convolution neural network and a recurrent neural network for feature extraction and class prediction correspondingly. The authors of [**?** ] propose a Maximum Entropy model for multilabel classification of short texts found in OSNs. Furthermore, they present an emotion per term lexicon as generated by the model, based on six basic emotions. However, they calculate a micro averaged F1 based on the top emotions per item, essentially converting each weighted label to binary format. Johnson and Zhang [**?** ] present a combination of word order and bag of words in a CNN architecture and point out the threshold sensitivity in multilabel classification.
