Skip to main content

Optimizing Outcomes by Manipulating Text

Depending on the level of insight you aim to produce, it can be necessary to take different approaches to structuring your text samples for analysis. For example, sentence-level analysis works best when you want to identify emotions related to key topics of interest. Or, you can split conversational language into chronological segments to evaluate linguistic progression over time. Below are several examples of different useful text concatenation methods:

Analysis of the Individual​

  • Use case: Understanding the character traits of a single person (i.e., speaker, author, leader, etc.).

  • Method: Concatenate all language data from a single speaker.

  • Example Objective: Assess the communication style of an executive leader to align and boost employee engagement and effectiveness. Collect the leader’s written or spoken language from company emails, instant messages, speeches, etc., and compile it into one cell of your CSV file.

Analysis of the Group​

  • Use case: Understanding the character traits of multiple individuals as a collective (i.e., speaker, author, leader, etc.).

  • Method: Concatenate all language data for each individual in the group separately. After scoring, calculate the average score for all individuals to ensure each person is weighted equally in the group average. Alternatively, if you prefer the group average to be weighted by word count—allowing more verbose individuals to contribute more to the final score—concatenate all language data for the group into a single sample before scoring.

  • Example Objective: Assess the personality and motivations of an audience segment to improve marketing and ad effectiveness. Collect audience-generated content (i.e., social media posts, focus group transcripts) and compile the language data based on author or segment depending on your preferred method.

Analysis of Answers to Key Questions​

  • Use case: Exploring and comparing trends in responses across individual questions.

  • Method: Aggregate language data based on individual questions.

  • Example Objective: Analyze and improve the communication style of customer support representatives to enhance customer satisfaction and resolution efficiency. Collect all written communications from customer support reps over a specified period, including emails and chat transcripts and compile the responses that were given in answer to each question.

Analysis of Answers by Question Theme​

  • Use case: Exploring and comparing trends in responses across multiple related questions.

  • Method: Aggregate language data based on question theme.

  • Example Objective: Analyze and categorize customer feedback and product reviews by thematic elements to better address common concerns, enhance product and service offerings, and improve marketing strategies. Collect reviews and combine the responses that were given in answer to each set of related questions.

Analysis of Conversation Over Time (Longitudinal)​

  • Use case: Evaluating trends in conversation progression or long-term progression.

  • Method: Split the language data into chronological segments; segments can be split based on word count, time, a conversation outline, days, weeks, etc.

  • Example Objective: Evaluate the changes in employee sentiment and communication trends across different fiscal quarters to better understand workforce morale and engagement. Compile transcripts of quarterly all-hands meetings into a single document, allowing for a comprehensive analysis of overarching themes and shifts.

Analysis of Intra-Person Variance (Non-Temporal)​

  • Use case: Understanding internal variability within an individual's communication style, such as thinking agility and tonal shifts in messaging—even when time is not the primary factor.

  • Method: Split a single individual's language into multiple equal-sized or contextually meaningful segments (e.g., paragraphs, questions, or topic transitions), regardless of timeline.

  • Example Objective: Evaluate the thinking agility of a speaker by dividing their full transcript into segments based on thematic shifts or rhetorical structure. This allows insight into how their tone, emotional stance, or thinking agility (as measured by fast and slow thinking) may vary across different parts of the same transcript—even without a temporal progression.

Analysis of Topics by Emotion​

  • Use case: Identifying emotions related to key topics of interest.

  • Method: Parse language data into sentences and score using pre-built or custom taxonomies and our emotions framework.

  • Example Objective: Evaluate the emotional responses elicited by different elements of marketing campaigns to optimize messaging and content for targeted audience engagement. Compile all customer interactions and feedback related to specific marketing campaigns, such as social media comments, survey responses, and customer service transcripts.

Analysis of Rapport (Language Style Matching)​

  • Use case: Understanding the extent to which two or more speakers are attentively engaged.

  • Method: Analyze and compare each speaker pair’s language.

  • Example Objective: Evaluate the linguistic alignment between job candidates and interviewers during interviews to identify strong rapport, which can indicate better team fit and communication compatibility. Use turn-by-turn text in VTT files or row-by-row in CVS files.

note

For best results, text should be split at sentence boundaries if possible — not in the middle of a sentence. This helps preserve linguistic coherence and helps ensure more accurate scoring. Each of the created sample segments should still meet word count minimum thresholds to ensure valid output.