A Consensus Approach to the Sentiment Analysis Problem Driven by Support-Based IOWA Majority

Abstract

In group decision making, there are many situations where the opinion of the majority of participants is critical. The scenarios could be multiple, like a number of doctors finding commonality on the diagnose of an illness or parliament members looking for consensus on an specific law being passed. In this article, we present a method that utilizes induced ordered weighted averaging (IOWA) operators to aggregate a majority opinion from a number of sentiment analysis (SA) classification systems, where the latter occupy the role usually taken by human decision‐makers as typically seen in group decision situations. In this case, the numerical outputs of different SA classification methods are used as input to a specific IOWA operator that is semantically close to the fuzzy linguistic quantifier ‘most of’. The object of the aggregation will be the intensity of the previously determined sentence polarity in such a way that the results represent what the majority think. During the experimental phase, the use of the IOWA operator coupled with the linguistic quantifier ‘most’ (IOWAmost) proved to yield superior results compared to those achieved when utilizing other techniques commonly applied when some sort of averaging is needed, such as arithmetic mean or median techniques.

Application of uninorms to market basket analysis

“…Uninorms, first introduced in, 15 have been widely used in aggregating variables for multi-criteria decision making, in modelling cardinal consistency of preferences, and in propagation of trust in social network. [16][17][18][19][20][21][22] In a study of customer satisfaction, Depaire et al 23 demonstrated that uninorms were superior to regression and correlated better with customer satisfaction theory. Similarly, uninorms have been shown to be effective in aggregating sentiments of experts in group decision making.…”

Computing Sentiment Analysis through Aspect-based fuzzy Aggregations

“…However, when a document encloses several phrases dealing with different aspects or entities, it is necessary to focus on the sentence level. This one is related to subjectivity classification, a subarea which distinguishes phrases expressing factual information from phrases containing more subjective views [20,2,4,3]. And finally, the finest-grained level is the aspect level, which considers a target on which the user expresses an opinion in a positive or negative sense [25,16,29].…”

“…Opinion from TripAdvisorThis opinion clearly expresses an arithmetic mean of the values of the aspects. The overall value is 4 bubbles which would be the average of the bubbles for each aspect(3,3,5,4,4,5).If this user's opinion were to be modeled through an OWA operator, greater weight would be given to the central values, for example through the vector W = {0.0, 0.2, 0.3, 0.3, 0.2, 0.0} being A σ = {3, 3, 4, 4, 5, 5}. The final result of the aggregation would also be 4.…”

Comparing global news sentiment using hesitant linguistic terms

“…25 They may be aggregated with simple means, such as the average, which is highly sensitive to outliers, or by more complex means, such as centroids, 26 interval-valued Pythagorean fuzzy numbers to include the correlation of a product's features, 21 or OWA operators, such as Induced Ordered Weighted Averaging (IOWA). 27 This paper presents a solution based on the distance defined in the lattice of hesitant linguistic terms.…”