Chapter 9- Social Media Marketing

Secondary research
information already collected and available for use; may be internal, published publicly, or available via syndicated sources
Primary research
is collected for the research purposes at hand; can help marketers to understand consumers in the market
Social media research
the application of scientific marketing research principles to collection and analysis of social media data such that valid and reliable results are produced
Observational research
involves recording behavior or the residual evidence of behavior
Social media listening and monitoring
is the most popular approach to social media; literally means to monitor conversations and content in social media channels by listening
Scraping
collecting conversations according to established criteria for inclusion in a database
Verbatims
the actual comments people post in English or other languages as well as identifying information such as the time the item was posted and the site on which it appeared
Research design
specifies a plan to collect and utilize data so that desired information can be obtained with sufficient precision and or so that hypothesis can be tested properly
Sentiment
refers to how people think or feel about an object such as a brand or a political candidate
Opinion mining
a very basic level to analyze content to determine the attitude of the writer
Word-phase dictionary
program will scan the text to identify whether the words in the dictionary appear
Text classifiers
once data are retained for further analysis the data can also be classified according to the words and phrases in the dictionary
Sentiment analysis
extract the entities of interest from the sentence, identifying the product
Text mining
gathering and analysis of text data from relevant source
Content analysis
an analysis approach used to identify the presence of concepts and themes within qualitative data sets, users a top-down approach that applies theory or empirical evidence to the coding process
Sample frame
an available list that approximates the population and from which we draw a sample to represent the population
Coverage error
occurs when there is a failure to cover all components of a population being studied
Sampling
refers to the process a researcher uses to select specific cases from a sampling frame for inclusion in a study
Sampling error
is the result of collecting data from only a subset, rather than all of the members of the sampling frame; it heightens the chances that the results are wrong
Participation effect
when only some people are participating and some participate at a high rate, effectively inflating the number of conversations that relate to the research
Echo effect/online echo
refers to the duplication in conversation volume that tends to occur in social media spaces; exists because people who share content online tend to share it in more than one community
non response error
the potential that those units that were not included in the final sample are significantly different from those that were
Sampling weights
are adjustment factors applied to adjust for differences in probability of selection between cases in a sample