Journal of Communication Research
Year:2019 | Volume:26 | Issue:2 (98)|Papers Count:7

Survey is a powerful and reliable way of gathering information and being aware of opinions, perceptions, attitudes, and even beliefs and values, and generally how the public think. Sensitive questions can be the ones that respondents feel vulnerable to. So, it is necessary to analyze the public knowledge of community under study, especially in terms of cultural characteristics and the level of public awareness about the subject under study due to research purposes. Valid, reliable, and interpretable results depend on predicting the likely sensitivities and objections of the respondents. There are special considerations by limited choices on how to deal with sensitive topics in all questionnaires. It seems that in different societies, the type and degree of sensitivity are different, due to cultural differences. Therefore, it is essential to obtain background information about the community under study. In this study, while identifying errors caused by direct queries on sensitive topics, we intend to introduce techniques, methods, or ways that minimize error and deviation in results while asking sensitive questions.

This article, while approving the ability of polling to find out public opinion, attempted to examine the areas of “ ineffectiveness of polling” at three levels of citizens, polling institutes, and officials. The main idea of the paper is that "ineffectiveness of polling" is the result of the constructing various factors that each of them are trying to promote, rather than based on the actual results of the polls. In polling institutes, some individuals and institutions attribute their failure to the analysis of polls whereas it is due to weak sociological vision and lack of commitment to scientific and organizational standards. In organizations that use poll results, some executives, who realize their power and benefits by ignoring people's voices, try to reduce the validity, importance, and impact of surveys by appealing to the ideology of professionalism and unprofessionalizing poll findings. In other words, some individuals and groups, with different motivations, have an interest in promoting the "idea of ineffectiveness of polling " in different domains, and are trying to make this point by reducing the "public credibility" of polls to "scientific credibility", and doubting the scientific credibility of the polls.

Today, planners and providers of goods and services are interested in knowing people's opinions about their product, so that they can meet the needs of users of goods and services and improve their position. Getting people's opinion on a particular topic is called polling. Polling is usually conducted through non-probability sampling methods. The problem with this method is that lack of accuracy in the results as in probability sampling to generalize to the whole population. Using this method provides only a description of the individuals in the sample. Using different sampling techniques can help to fix this shortcoming. In this article, while briefly referring to non-probability and probability sampling methods, the advantages of using probability methods in polling will be outlined. Also, the concept of rotation sampling and its advantages over other sampling methods will be discussed and suggested for use in surveys.

The concept of literacy today, has been transformed from the ability to read and write, or the ability to use language to read, write, listen and speak, which only provides the initial aspect of communication, to understand concepts, ideas and thoughts. A "literate" refers to a person who is capable of knowing, understanding, interpreting, constructing, communicating, and using printed and written material in a variety of contexts. Statistics literacy is a very important skill in dealing with data and statistical information that is growing rapidly today. As this basic skill is developed, followed by public demands and the desire to use statistics and statistics to build a better life, it is important to pay attention to this need. As this basic skill is developed, and subsequently, the public demands and desire to use statistics and statistic information to build a better life, meeting this need is important. Therefore, survey as a technique for collecting, converting data into accurate information and reporting requires a general culture. In other word, statistical literacy can grow in a context of public culture that is supported both by surveying and data gathering groups including 'producers', 'consumers' and 'participants', as well as by caring for their transformation and presentation. Accordingly, the present paper attempts to provide a framework in this regard.

The question is how the complementary and alternative methods can be used while preserving the capabilities and benefits of the survey and polling research, given the relatively limited range of these methods. To find the right answer to this question, and after reviewing methodological explanations and reviews, as well as the various experiences gained, a more efficient model has been suggested for applying this type of research by comparing the features of other methods and taking advantage of the possibilities of other methods to compensate for deficiencies that may arise in information gathering, information analysis, interpretations and final conclusions. As a complementary approach, it is recommended to use a focused group discussion in each of the stages of the survey research. As alternative approaches, it has been attempted to show that by excluding any of the features of survey research, which of the proposed alternative methods, namely ethnography, participatory practical research, case study, and content analysis, can be used.

Measuring attitude does not end with data analysis but is the beginning of a way through which can increase the quality of attitudinal analysis and provide an opportunity to reduce measurement error. In this study, the difference between the classical test theory (CTT) and item response theory (IRT) in determining the psychometric properties of the data obtained from polling is studied. Before presenting the results of the analysis of these two theories, exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) were also used to evaluate constructing, validity and reliability of the tools. The subject of the study was actual data on the opinion polls of 3684 people from different groups about television programs. The findings show that both classical test theory and item response theory can provide similar information about the scale items of the latent feature under study. But the two measurement theories give different images of the accuracy of the scales. In general, item response theory offers both more information about measurement accuracy and clearer suggestions for scale improvement.

Providing accurate estimates of the turnout and estimating the votes of candidates is always of interest to individuals, parties, factions, groups and political and social institutions in the country. By Providing a solution for missing data of statistical population units and post-stratified sampling, Better results can be obtained to estimate the participation and votes of candidates than other probability sampling methods. The effects of the sampling plan and post-stratified sampling on analytical statistics led to accurate estimates using sample averages that had previously been neglected in the practical analysis of election polling.