Citation Context

...ntification of a valid tweet, this component adds a sentiment triple to its RDF representation. More specifically, we used a dictionary-based sentiment classifier provided by the Universitá di Trento =-=[13]-=-, which was extended by positive and negative emotion patterns. Dictionary-based sentiment classifiers are known to be efficient for short texts concentrating on a single topic, such as tweets. A sent...

Citation Context

...n a time series of numeric values, s(t), which is derived from raw sentiments S(t) for a particular topic T and represents some sentiment feature or interestingness measure, e.g., contradiction level =-=[15]-=-. These time series are shown in Figure 1 ( top), where s(t) represents the contradiction level of raw sentiments S(t). Along with the sentiment time series, we are given the news frequency time serie...

Citation Context

...otator agreement on the “controversy” label is very challenging. Additionally, while intuition and some researchers might suggest that the notion of sentiment should be relevant for controversy (e.g. =-=[32, 39]-=-), others have argued that sentiment is not the right metric by which to measure controversy [3, 12, 27]; opinions on movies and products may contain sentiment, yet lack controversy. Likewise, we find...

Citation Context

...sputes, but also from disagreement on values or from moral debates. Sentiment analysis can naturally be seen as a useful tool as a step towards detecting varying opinions, and potentially controversy =-=[5, 15, 18]-=-. However, as mentioned elsewhere [3, 7], sentiment alone may not suce for detecting controversy, though it may be useful as a feature. 3 Nearest Neighbor approach Our approach to detecting controver...

Citation Context

...collection of individual files (Figure 3, right). The additional benefit of this organization is that it ensures fast sequential access for time series of sentiments, compared to relational databases =-=[16]-=-. We note that the number of sentiment values monotonically decreases as we navigate down the demographics lattice and down the DTree levels, so many of the demographics leaf nodes will contain zeroes...

Citation Context

...the previous projects in Politecnico di Milano (i.e, BOTTARI [3], Social Listening of London Olympics 2012 [4]) and University of Trento (i.e., sentiment mining and contradiction detection on the Web =-=[5]-=-). The remainder of this paper is organised as follows. Section 2 describes the data sources that TF integrates, the architecture of TF and how it processes the social streams from Twitter and Instagr...

Citation Context

...hich can be analyzed coherently with the news time series in order to extract correlations. The particular methods which can be adopted to our problem are sentiment volume [4] and contradiction level =-=[8]-=-, discussed below. Sentiment Volume is defined as the amount or the sum of sentiments of a particular polarity, expressed within a specified time interval [4]. It captures bursts of particular opinion...

Citation Context

...ce of the effectiveness of our CSE Entities Decorator. Type of Link Number of Links Correctness Visitor-Venue 761 72% Visitor-CSE 3723 94% The decoration phase is concluded by the Sentiment Decorator =-=[22]-=- that adds the sentiment information to the tweet. It relies on a dictionary-based classification method, and applies the same processing for tweets written in English and in Italian. More specificall...