Judging Instinct Exploitation in Statistical Data Explanations Based on Word Embedding
Judging Instinct Exploitation in Statistical Data Explanations Based on Word Embedding
复制标题
DOI：
10.1145/3514094.3534171
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Kang Zhang;Hiroaki Shinden;Tatsuki Mutsuro;Einoshin Suzuki
中科院分区：
文献类型：
--
作者：
Kang Zhang;Hiroaki Shinden;Tatsuki Mutsuro;Einoshin Suzuki
本文提出了18种类型的统计数据解释和3种程序，以调查由于利用Rosling等人提出的10种本能而导致的不道德和有偏见的解释的可信度。"女性数学成绩低于男性"的解释及其平均值和分数分布是这种解释的一个例子，因为它利用了差距本能，我们倾向于把所有的东西分成两个不同的，往往相互冲突的群体。如果我们用“英语”代替“数学”，即使我们保持数据不变，它也会变得不那么可信，因为开发似乎失败了。我们的判断程序是基于短语嵌入和精心设计的比较来判断可信度。我们的实验结果比较的18种类型与它们的变体显示出有希望的结果和线索，为进一步的发展。
This paper proposes 18 types of statistical data explanations and three kinds of procedures to investigate credibility in unethical and biased explanations due to exploitation of the 10 instincts proposed by Rosling et al. The explanation "women have lower math scores than men'' accompanied with the averages and the distributions of their scores is an example of such an explanation, as it exploits the gap instinct, i.e., our tendency to divide all kinds of things into two distinct and often conflicting groups. It becomes much less credible if we replace the word "math'' with "English'', even if we keep the data as they are, as the exploitation seems to fail. Our judging procedures are based on phrase embedding and carefully designed comparisons to judge the credibility. The results of our experiments comparing the 18 types with their variants show promising results and clues for further developments.