The impact of political party/candidate on the election results from a sentiment analysis perspective using #AnambraDecides2017 tweets

Abstract

This work investigates empirically the impact of political party control over its candidates or vice versa on winning an election using a Natural Language Processing (NLP) technique called Sentiment Analysis (SA). To do this, a set of 7430 tweets bearing or related to #AnambraDecides2017 was streamed during the November 18, 2017 Anambra State gubernatorial election. These are Twitter discussions on the top 5 political parties and their candidates termed political actors in this paper. We conduct polarity and subjectivity sentiment analyses on all the tweets considering time as a useful dimension of SA. Furthermore, we use the word frequency to find words most associated to the political actors in a given time. We find most talked about topics using a topic modeling algorithm and how the computed sentiments and most frequent words are related to the topics per political actor. Among other things, we deduced from the experimental results that even though a political party serves as a platform that sales the personality of a candidate, the acceptance of the candidate/party adds to the winning of an election. For example, we found the winner of the election Willie Obiano benefiting from the values his party share among the people of the State. Associating his name with his party All Progressive Grand Alliance (APGA) displays more positive sentiments and the Subjective Sentiment Analysis indicates that Twitter users mentioning APGA are less emotionally subjective in their tweets than the other parties.

Identification of affective valence of Twitter generated sentiments during the COVID-19 outbreak

“…Sentiment analysis can cluster or classify social media posts based on polarity, i.e., polarity (negative, positive, neutral; see Gaspar et al 2016 ). Advanced SA techniques can identify subjectivity (fact and opinion) (Onyenwe et al 2020 ), a variety of emotions or sentiments such as happiness and sadness (Ali et al 2017 ; Gao et al 2016 ), concern, surprise, disgust or confusion (Ji et al 2016 ). Some SA programs can also identify the object of an expression in addition to its sentiment (e.g., the color is nice but it is too loud: this is “negative”; Sloan and Quan-Haase 2017 , p-546).…”

A review on sentiment analysis and emotion detection from text

“…Sentiment analysis is defined as the process of obtaining meaningful information and semantics from text using natural processing techniques and determining the writer’s attitude, which might be positive, negative, or neutral (Onyenwe et al. 2020 ). Since the purpose of sentiment analysis is to determine polarity and categorize opinionated texts as positive or negative, dataset’s class range involved in sentiment analysis is not restricted to just positive or negative; it can be agreed or disagreed, good or bad.…”

Public opinion monitoring through collective semantic analysis of tweets

“…Similarly, in Onyenwe et al. ( 2020 ), tweets about the 2017 Anambra State gubernatorial election in Nigeria are semantically analyzed and the outcomes are aggregated for every 2-h interval posts. The produced time-series cover an 18-h time-frame on the election day.…”

“…The only case where multidimensional semantics are considered is Onyenwe et al. ( 2020 ), where 2 different opinion dimensions (polarity and bias) are both taken into account. In contrast, this paper proposes a 4-dimensional mechanism jointly considering polarity, bias, figurativeness and offensiveness, which are all different text attributes, and experimentally verifies their usefulness .…”