This module allows an in-depth analysis of the SBS_associations.csv file produced by the main SBS analysis. Please upload the SBS_associations.csv file previously produced by the SBS analysis without changing its name or content (encoding must always be “utf-8”).
Basic textual metrics are calculated at every run (such as counting the number of associations). In addition, you can choose to carry out these other more advanced analyses:
Dimensions: this field can be used to specify custom dimensions for the analysis of the brand image. You can use a dictionary to represent each dimension. The following syntax has to be used
"dimension_name1":["word1","word2",..], "dimension_name2":["word6","word8",..],... It is possible to repeat the same word in different dimensions. Please use the lowercase. Hyphens will be replaced by whitespaces, such that if "zero-emission" is used, the software will count both "zero-emission" and "zero emission". The dimension name will not be considered as a word for the analysis. Additionally, asterisks can be used at the end of words, indicating that a specific word could be completed with any possible set of characters. For example, if the word
"asp*"is used, this will match both the words
"aspire". This does not work with multiple words.
Language: this is the language used for the analyses described in the following.
Analyses: similarly to the Text Analysis function, you could choose to analyze brand associations by considering:
Complexity: calculates the language complexity of each brand’s associations. The function provides several metrics: the number of words of six or more letters (absolute and relative frequencies), the average word length, and other complexity scores calculated using the TF-IDF function and considering the word frequency distribution. The function also calculates the numerical intensity and readability of the text (Gunning-Fog index).
Emotions partial: calculates several dimensions of the language used (such as the degree of positive and negative emotions or the language orientation towards the past or future). Scores are normalized considering the length of the document and can range from 0 to 100. To obtain the raw scores, you can multiply values by WordCountOriginal and divide by 100. Some scores might be zero if you removed stop-words during the SBS analysis that produced the associations’ file.
Emotions full: calculates additional emotions, such as anger or joy, as well as scores for valence, dominance, and arousal. These scores are inspired by the NRC lexicon (for more information, see https://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm). Valence, dominance, and arousal can be positive or negative (without a predefined range). The other emotion scores are normalized considering the length of the document and can range from 0 to 100. To obtain the raw scores, you can multiply by WordCountOriginal and divide by 100.Some scores might be zero if you removed stop-words during the SBS analysis that produced the associations’ file.
Crovitz: calculates the relative frequencies of the Crovitz’s relational words that appear in brands’ associations. Some scores might be zero if you removed stop-words during the SBS analysis that produced the associations’ file.
Sentimentis not an option here, as it is already calculated for each brand (and time interval) by the main SBS analysis (which has been used to produce the SBS_associations.csv file). You will still get the values of positive and negative emotions from the other lexicons (NRC, Loughran-McDonald, etc.)
The Image Explorer module generates up to three files:
AssoDimensionsOverall, but for each time interval.
_reldimare calculated considering the total number of matching associations in each time interval and the total number of matching associations in a time interval with respect to the other brands.