-
Racial Filtering Classification Model Through Data Analysis of Racial Contents in Twitter
Jung-hun Baeck,
Teresa Hyoju Chang,
Jaden Chunho Chyu,
Bryan Chunwoo Chyu,
Chaehyun Lim
Issue:
Volume 7, Issue 6, December 2021
Pages:
132-138
Received:
23 September 2021
Accepted:
20 October 2021
Published:
10 November 2021
Abstract: Stop Asian Hate or Stop Asian American Pacific Islanders (AAPI) Hate refers to the national movement against racially-motivated attacks on Asians. This protest was initiated in line with the Black Lives Matter (BLM) movement, to dismantle the ongoing hate and targeted crimes against Asians, and to educate people of such threats. Hate crimes targeting Asians have been occurring steadily across the U.S, but with the effect of COVID-19, these crimes started increasing in number. For the Stop Asian Hate movement, the matter was exacerbated with people accusing certain Asian countries as the source for COVID-19. In 2021, Asian Americans reported a single biggest increase in serious incidents of online hate and harassment with racist and xenophobic slurs blaming people of Asian descent for the spread of COVID-19. To specifically assess the impacts and measures of each movement, research was conducted to examine the racial slurs used towards Asians on social media, specifically Twitter. For analysis of the data on social media, Python programming was used to collect and analyze the ratio of racial slurs and Anti-Asian hate. In doing so, the data set was modeled through data labeling, which classified each social media tweet into one of three sub-categories. Data were classified into two types: type 1 that contains racial contents or information against Asians and type 0 that has non-racial contents. The data collection was done through Twint, a Python scraping tool for Twitter, gathering a total of over 2,000 recent tweets for keywords relevant to the movement. Then, a preprocessing step was taken through Python, involving the process of decapitalizing, lemmatizing, and tokenizing. These data were then represented by graphs and word clouds, displaying some of the most commonly used terms targeting Asians on social media. Lastly, the data went through a design of a binary classification model for filtering tweets with racial content. We compared the accuracy of classification models with three different algorithms: logistic regression, random forest, and SVM. The model created would be able to safeguard users from exposures to racist terms vastly pervaded on the internet.
Abstract: Stop Asian Hate or Stop Asian American Pacific Islanders (AAPI) Hate refers to the national movement against racially-motivated attacks on Asians. This protest was initiated in line with the Black Lives Matter (BLM) movement, to dismantle the ongoing hate and targeted crimes against Asians, and to educate people of such threats. Hate crimes targeti...
Show More
-
Modeling Domestic Price Volatility for Cereal Crops in Ethiopia
Issue:
Volume 7, Issue 6, December 2021
Pages:
139-149
Received:
28 March 2021
Accepted:
2 November 2021
Published:
12 November 2021
Abstract: The volatility in the domestic prices of maize and teff crops has been found to vary over time from month to month. Thus, Families of time series models namely, ARCH with their extensions to generalized ARCH, GARCH and EGARCH models with ARIMA mean equations were considered to the data. The best fitting model among each family of models was selected based on how well the model captures the variations in the data. The optimal lag specification for the models are accessed via AIC and SBIC. Comparisons of the symmetric and asymmetric selected models were carried out based on the significance of asymmetric term in the EGARCH model. Thus, statistically significance of asymmetric term and least forecast error from the model established that the EGARCH model with GED for residuals was superior to the GARCH model. Therefore, the ARIMA(2,0,3)-EGARCH(1,1) and ARIMA(0,0,3)-EGARCH(2,3) were chosen to be the best fitting models among the ARIMA(p, d, q)-GARCH(P, Q) family for monthly domestic price volatility of maize and teff crops, respectively. However, the volatility in the domestic price of wheat and barley was found to be not changing over time. Hence, the variance of the ARIMA process was used as the measure of volatility in the prices of these two crops which were 0.00112 and 0.0004, respectively. Moreover, it was found that from candidate exogenous variables, import prices for maize crop, fuel oil price, exchange rate (dollar-birr), inflation from non-food items, past shock and volatility on the domestic price had statistically significant effect on the current month domestic price volatility for maize and teff crops.
Abstract: The volatility in the domestic prices of maize and teff crops has been found to vary over time from month to month. Thus, Families of time series models namely, ARCH with their extensions to generalized ARCH, GARCH and EGARCH models with ARIMA mean equations were considered to the data. The best fitting model among each family of models was selecte...
Show More
-
A Machine Learning Approach for the Short-term Reversal Strategy
Zheng Tan,
Yan Li,
Chulwoo Han
Issue:
Volume 7, Issue 6, December 2021
Pages:
150-160
Received:
25 October 2021
Accepted:
12 November 2021
Published:
17 November 2021
Abstract: The short-term reversal effect is a pervasive and persistent phenomenon in worldwide financial markets that has been found to generate abnormal returns not explainable by traditional asset pricing models. In contrast to the linear model employed in most studies on the short-term reversal, this article aims to establish a nonlinear framework to study the reversal anomaly, by using machine learning approaches. Machine learning methods including Random Forest, Adaptive Boosting, Gradient Boosted Decision Trees and extreme Gradient Boosting, are employed to test the profitability of the short-term strategy in the US and Chinese stock markets. Significant outperformances with extremely high Sharpe ratio, moderate kurtosis, and positive skewness are found, showing remarkable classification efficiency of the machine learning models and their applicability to various markets. Further studies reveal that the strategy returns can be weakened with the extension of the holding period. Notably, by comparing the performances of machine learning with our newly developed linear reversal strategy, the nonlinear methods are proved to be capable of providing a diversified model predictability with improved classification accuracy. Our research indicates the significant potential of machine learning in resolving the stock return and feature relationship, which can be helpful for quantitative traders to make profitable investment decisions.
Abstract: The short-term reversal effect is a pervasive and persistent phenomenon in worldwide financial markets that has been found to generate abnormal returns not explainable by traditional asset pricing models. In contrast to the linear model employed in most studies on the short-term reversal, this article aims to establish a nonlinear framework to stud...
Show More
-
Trends of Armed Conflict in Kenya from 1997 to 2021: An Exploratory Data Analysis
Peter Kimani,
Caroline Mugo,
Henry Athiany
Issue:
Volume 7, Issue 6, December 2021
Pages:
161-171
Received:
20 October 2021
Accepted:
26 November 2021
Published:
2 December 2021
Abstract: Armed conflict patterns have drastically changed since the post-cold war period. In Sub-Saharan Africa, armed conflict continues to be persistent and on the rise. Kenya has not experienced civil war, but has experienced intra-state conflicts which display themselves as political, natural resources, ethnicity, land, and environmental conflicts. This study aimed to identify patterns and trends of armed conflict in Kenya. Secondary data from Armed Conflict and Location Events Data (ACLED) for the period 15th January 1997 to 25th February 2021 was used. Exploratory data analysis and generalized additive model were used to identify patterns and trends. For the period studied, 7,437-armed conflict events and 11,071 fatalities were recorded. There was a non-linear trend and a general increase in the number of armed conflict cases in Kenya. The peaks in the non-linear trend were observed during the years 2002, 2007, 2013 and 2017. On the contrary, the number of fatalities from armed conflict decreased over time and had a non-linear trend, with peaks in the years 1998, 2001, 2007, 2013 and, 2017. Similarly, there was a reduction in the number of fatalities per armed conflict over time with 149 fatalities per 100-armed conflict events recorded in the study period. Linear and non-linear trend of armed conflict events was observed at the county levels, with counties like Nairobi and Nakuru having a non-linear trend similar to the overall trend. The number of events of armed conflict for riots and protests event type had a non-linear trend while the rest had a linear trend with a positive slope. Violence Against Civilians (VAC) event type had the highest number of events followed by Riots and Protests. Additionally, VAC had the highest number of fatalities followed by Battles and Riots. In terms of fatalities per armed conflict, Explosions/Remote violence event type had the highest fatality rate followed by Battles and VAC. The peaks in the number of armed conflict cases and fatalities were observed in the years in which general elections were conducted in Kenya.
Abstract: Armed conflict patterns have drastically changed since the post-cold war period. In Sub-Saharan Africa, armed conflict continues to be persistent and on the rise. Kenya has not experienced civil war, but has experienced intra-state conflicts which display themselves as political, natural resources, ethnicity, land, and environmental conflicts. This...
Show More