Human Information Interaction

---

Background and Aim: In processing large data, scientists have to perform the tedious task of analyzing hefty bulk of data. Machine learning techniques are a potential solution to this problem. In citizen science, human and artificial intelligence may be unified to facilitate this effort. Considering the ambiguities in machine performance and management of user-generated data, this paper aims to explain how machine learning can be combined with the active citizenship concept. In addition, it discusses the necessary conditions for advancing the citizen science and beyond.
Method: The review method and comprehensive systematic study was applied to assess the concept of machine learning, citizen science and human-computer interaction.
Results: Many research problems seem to be computationally insolvable and may demand human cognitive skills. Therefore, due to classification activities which are performed in the majority of large-scale citizenship science projects, in addition to participants who may learn lessons about the science, machines also learn lessons about human and imitate him and slowly its learning capacity enhances over time. Artificial intelligence, particularly machine learning is a debatable topic with related ambiguities and biases which should strongly take into consideration.
Conclusion: The application of machine learning techniques carries many advantages including classification time cut and masterful evaluations in the process of making decisions on big data sets. However, algorithms usually act as a black box where data biases are not observable at first glance. Taking this problem into consideration may mitigate serious risks arising from the application of such techniques.

---

Abstract: Researchers emphasize the role of digital annotation technologies and tools in teaching and learning. The purpose of the present study was to improve the learning and reading experience of users about vocabulary by using different types of annotations (audio, phonetic transcription). The approach of this research was quantitative and the research method was semi-experimental and its design was pre-test-post-test. The statistical population are users with no knowledge of Persian language. In order to carry out the research, 30 non-Persian speaking users were selected from the statistical population using a non-probability and targeted sampling method and were randomly assigned into two experimental and control groups (15 people in the experimental group and 15 people in the control group). The tools used in this research were two questionnaires to perform practical work, one questionnaire in the pre-test stage and one questionnaire in the post-test stage. After the pre-test, the experimental group received support such as adding an interactive tutorial introducing the work program and IPA to users in order to improve the learning experience and strengthen reading. While the control group did not benefit from this intervention during the research process. The results showed that there is a significant difference between the reading scores between the experimental and control groups. Also, a significant difference was observed between the pre- and post-test scores in the experimental group. But this difference before and after the test was not observed in the control group. The average scores of users' learning and reading experience in the control group before the international transliteration training is equal to 18.6 and after the international transliteration training is 19.8, while the average scores of the users' learning and reading experience in the experimental group before the transliteration training International is equal to 1.19 and after the training of international transliteration, it has increased to 2.23. Also, in the pre-test stage, the average distance from the correct answer (error rate) of the experimental group was 4.09 and in the post-test stage, it reached 1.1, showing a significant decrease. In the control group, the average distance from the correct answer (error rate) of people was 3.4 and in the post-test stage it reached 3.6, which did not change much. Therefore, according to the above evidence, it can be said that the types of annotations (audio, transliteration) have resulted in a significant change in the learning and reading experience of users, and international transliteration training has been effective as a method to support the learning and reading experience of users.