PERSEUS: A Personalization Framework for Sentiment Categorization with Recurrent Neural Network

Personalized Sentiment Analysis and a Framework with Attention-Based Hawkes Process Model

“…Length of the History An experiment is conducted with different numbers of past tweets added in the input sequence. Results are shown in Table 3 as reported in our previous work [13]. The performance is poor while considering one past tweet, because the possibility of having meaningful relations between two consecutive tweets is relatively low.…”

“…In [13], we have proposed a personalized model which aims at investigating the effectiveness of including individualities in sentiment analysis. With respect to individualities, the following assumptions were considered: Assumption I: Different individuals make different lexical choices to express their opinions.…”

“…Note that we do not compare the performance of the P-model with the reported results of SemEval because different test data are used for the evaluation, as explained in Section 5.2. The comparison is shown in Table 2 as in our earlier publication [13]. In the same way as for the P-model, concept-based representation is used for the baseline models.…”

“…In this article, we introduce a framework with neural networks to model individualities in expressing opinions, which intrinsically offers a solution for the data sparsity in the setting of social networks. This framework is developed based on the firststage results of PERSEUS [13] which evaluates the effectiveness of including users' historical text for determining the sentiment of the current text. Twitter data was used for the evaluation in the first stage and was used in the improved framework as well.…”